The Supermagin Leaderboard
Models verified on Supermagin lead the board. Every score comes from a real, published run, credibility-weighted and re-verifiable. Below them, every current model with real specs; run the official eval to earn a verified score.
Prove your model: run the official eval2
Verified in Supermagin
400
Overall top models
3
Attested runs
| Model | Score | Context | Input / Output ($/1M) | Thinking | Verified |
|---|---|---|---|---|---|
| Verified Verified in Supermagin · 2 models | |||||
 | 92 33% credible · 5 runs | 262K | $0.6 / $3.6 | Thinking | Verified |
 | 74 38% credible · 6 runs | 1.0M | $3 / $15 | Thinking | Verified |
| Overall top models · 398. Run the official eval to get verified | |||||
 Claude Opus 5 | 63 | 1M | $5 / $25 | Thinking | Test it in the Studio |
| Claude Opus 5 (batch) | 63 | 1M | $2.5 / $12.5 | Thinking | Test it in the Studio |
| Anthropic: Claude Fable 5 | 62 | 1M | $10 / $50 | Thinking | Test it in the Studio |
| Anthropic: Claude Fable 5 (batch) | 62 | 1M | $5 / $25 | Thinking | Test it in the Studio |
 SpaceXAI: Grok 4.6 | 61 | 500K | $2 / $6 | Thinking | Test it in the Studio |
 OpenAI: GPT-5.6 Sol | 61 | 1.1M | $2 / $10 | Thinking | Test it in the Studio |
| OpenAI: GPT-5.6 Sol (batch) | 61 | 1.1M | $1 / $5 | Thinking | Test it in the Studio |
ZZ.ai: GLM 5.3 | 60 | 1.0M | $1.4 / $4.4 | Thinking | Test it in the Studio |
| Qwen: Qwen3.8 Max | 58 | 1M | $2 / $6 | Thinking | Test it in the Studio |
| Qwen: Qwen3.8 2.4T A95B | 58 | 1.0M | $2 / $6 | Thinking | Test it in the Studio |
| Anthropic: Claude Opus 4.8 | 57 | 1M | $5 / $25 | Thinking | Test it in the Studio |
| Anthropic: Claude Opus 4.8 (batch) | 57 | 1M | $2.5 / $12.5 | Thinking | Test it in the Studio |
 Meta: Muse Spark 1.2 | 57 | 1.0M | $1.25 / $4.25 | Thinking | Test it in the Studio |
| OpenAI: GPT-5.6 Terra | 57 | 1.1M | $2 / $12 | Thinking | Test it in the Studio |
| OpenAI: GPT-5.6 Terra (batch) | 57 | 1.1M | $1 / $6 | Thinking | Test it in the Studio |
| OpenAI: GPT-5.5 | 56 | 1.1M | $5 / $30 | Thinking | Test it in the Studio |
| OpenAI: GPT-5.5 (batch) | 56 | 1.1M | $2.5 / $15 | Thinking | Test it in the Studio |
 Google: Gemini 3.7 Flash | 56 | 1.0M | $0.38 / $1.88 | Thinking | Test it in the Studio |
| Google: Gemini 3.7 Flash (batch) | 56 | 1.0M | $0.19 / $0.94 | Thinking | Test it in the Studio |
| SpaceXAI: Grok 4.5 | 56 | 500K | $2 / $6 | Thinking | Test it in the Studio |
| Anthropic: Claude Sonnet 5 | 55 | 1M | $2 / $10 | Thinking | Test it in the Studio |
| Anthropic: Claude Sonnet 5 (batch) | 55 | 1M | $1 / $5 | Thinking | Test it in the Studio |
| Anthropic: Claude Opus 4.7 | 55 | 1M | $5 / $25 | Thinking | Test it in the Studio |
| Anthropic: Claude Opus 4.7 (batch) | 55 | 1M | $2.5 / $12.5 | Thinking | Test it in the Studio |
 DeepSeek: DeepSeek V4 Pro 0813 | 53 | 1.0M | $1.12 / $3.37 | Thinking | Test it in the Studio |
| Meta: Muse Spark 1.1 | 53 | 1.0M | $1.25 / $4.25 | Thinking | Test it in the Studio |
| OpenAI: GPT-5.4 | 53 | 1.1M | $2.5 / $15 | Thinking | Test it in the Studio |
| OpenAI: GPT-5.4 (batch) | 53 | 1.1M | $1.25 / $7.5 | Thinking | Test it in the Studio |
ZZ.ai: GLM 5.2 | 53 | 1.0M | $1.19 / $3.74 | Thinking | Test it in the Studio |
ZZ.ai: GLM 5.2 (batch) | 53 | 1.0M | $1.4 / $4.4 | Thinking | Test it in the Studio |
ZZ.ai: GLM 5.2 (free) | 53 | 256K | Thinking | Test it in the Studio | |
| OpenAI: GPT-5.6 Luna | 52 | 1.1M | $0.2 / $1.2 | Thinking | Test it in the Studio |
| OpenAI: GPT-5.6 Luna (batch) | 52 | 1.1M | $0.1 / $0.6 | Thinking | Test it in the Studio |
| Qwen: Qwen3.8 27B | 52 | 1M | $0.43 / $2.55 | Thinking | Test it in the Studio |
| Google: Gemini 3.5 Flash | 52 | 1.0M | $1.5 / $9 | Thinking | Test it in the Studio |
| Google: Gemini 3.5 Flash (batch) | 52 | 1.0M | $0.75 / $4.5 | Thinking | Test it in the Studio |
| DeepSeek: DeepSeek V4 Flash 0731 | 52 | 1.3M | $0.06 / $0.12 | Thinking | Test it in the Studio |
| Google: Gemini 3.6 Flash | 52 | 1.0M | $0.75 / $3.75 | Thinking | Test it in the Studio |
| Google: Gemini 3.6 Flash (batch) | 52 | 1.0M | $0.38 / $1.88 | Thinking | Test it in the Studio |
| Anthropic: Claude Sonnet 4.6 | 48 | 1M | $3 / $15 | Thinking | Test it in the Studio |
| Anthropic: Claude Sonnet 4.6 (batch) | 48 | 1M | $1.5 / $7.5 | Thinking | Test it in the Studio |
| Google: Gemini 3.1 Pro Preview | 48 | 1.0M | $2 / $12 | Thinking | Test it in the Studio |
| Google: Gemini 3.1 Pro Preview (batch) | 48 | 1.0M | $1 / $6 | Thinking | Test it in the Studio |
| Qwen: Qwen3.7 Max | 47 | 1M | $1.48 / $4.43 | Thinking | Test it in the Studio |
MMiniMax: MiniMax M3 | 45 | 1.0M | $0.3 / $1.2 | Thinking | Test it in the Studio |
MMiniMax: MiniMax M3 (batch) | 45 | 524K | $0.3 / $1.2 | Thinking | Test it in the Studio |
MMiniMax: MiniMax M3 (free) | 45 | 1.0M | Thinking | Test it in the Studio | |
| DeepSeek: DeepSeek V4 Pro 0423 | 45 | 1.0M | $0.87 / $1.74 | Thinking | Test it in the Studio |
| MoonshotAI: Kimi K2.6 | 45 | 262K | $0.95 / $4 | Thinking | Test it in the Studio |
| MoonshotAI: Kimi K2.7 Code | 43 | 262K | $0.67 / $3.4 | Thinking | Test it in the Studio |
| MoonshotAI: Kimi K2.7 Code (batch) | 43 | 262K | $0.95 / $4 | Thinking | Test it in the Studio |
XXiaomi: MiMo-V2.5-Pro | 43 | 1.1M | $0.44 / $0.87 | Thinking | Test it in the Studio |
TThinking Machines: Inkling | 42 | 1.0M | $0.95 / $4.05 | Thinking | Test it in the Studio |
TThinking Machines: Inkling (batch) | 42 | 524K | $1 / $4.05 | Thinking | Test it in the Studio |
TThinking Machines: Inkling (free) | 42 | 1.0M | Thinking | Test it in the Studio | |
TTencent: Hy3 preview | 42 | 262K | $0.18 / $0.6 | Thinking | Test it in the Studio |
| DeepSeek: DeepSeek V4 Flash 0423 | 42 | 1.0M | $0.09 / $0.18 | Thinking | Test it in the Studio |
NNex AGI: Nex-N2-Pro | 42 | 262K | $0.25 / $1 | Thinking | Test it in the Studio |
UUpstage: Solar Pro 4 | 42 | 524K | $0.03 / $0.12 | Thinking | Test it in the Studio |
TThinking Machines: Inkling Small | 41 | 1.0M | $0.45 / $1.2 | Thinking | Test it in the Studio |
TThinking Machines: Inkling Small (free) | 41 | 1.0M | Thinking | Test it in the Studio | |
ZZ.ai: GLM 5.1 | 41 | 205K | $1.26 / $3.96 | Thinking | Test it in the Studio |
| OpenAI: GPT-5.4 Mini | 41 | 400K | $0.75 / $4.5 | Thinking | Test it in the Studio |
| OpenAI: GPT-5.4 Mini (batch) | 41 | 400K | $0.38 / $2.25 | Thinking | Test it in the Studio |
| SpaceXAI: Grok Build 0.1 | 41 | 256K | $1 / $2 | Thinking | Test it in the Studio |
| Qwen: Qwen3.6 Plus | 41 | 1M | $0.33 / $1.95 | Thinking | Test it in the Studio |
| OpenAI: GPT-5.4 Nano | 40 | 400K | $0.2 / $1.25 | Thinking | Test it in the Studio |
| OpenAI: GPT-5.4 Nano (batch) | 40 | 400K | $0.1 / $0.63 | Thinking | Test it in the Studio |
| Qwen: Qwen3.7 Plus | 39 | 1M | $0.32 / $1.28 | Thinking | Test it in the Studio |
MMiniMax: MiniMax M2.7 | 39 | 205K | $0.3 / $1.2 | Thinking | Test it in the Studio |
MMiniMax: MiniMax M2.7 (free) | 39 | 197K | Thinking | Test it in the Studio | |
 NVIDIA: Nemotron 3 Ultra | 38 | 512K | $0.6 / $3.6 | Thinking | Test it in the Studio |
| NVIDIA: Nemotron 3 Ultra (batch) | 38 | 512K | $0.6 / $3.6 | Thinking | Test it in the Studio |
| NVIDIA: Nemotron 3 Ultra (free) | 38 | 1M | Thinking | Test it in the Studio | |
XXiaomi: MiMo-V2.5 | 38 | 1.1M | $0.14 / $0.28 | Thinking | Test it in the Studio |
| SpaceXAI: Grok 4.3 | 38 | 1M | $1.25 / $2.5 | Thinking | Test it in the Studio |
LLing-3.0-flash | 38 | 262K | $0.02 / $0.06 | Thinking | Test it in the Studio |
| OpenAI: GPT-5.1 | 38 | 400K | $1.25 / $10 | Thinking | Test it in the Studio |
| OpenAI: GPT-5.1 (batch) | 38 | 400K | $0.63 / $5 | Thinking | Test it in the Studio |
| Google: Gemini 3.5 Flash Lite | 37 | 1.0M | $0.3 / $2.5 | Thinking | Test it in the Studio |
| Google: Gemini 3.5 Flash Lite (batch) | 37 | 1.0M | $0.15 / $1.25 | Thinking | Test it in the Studio |
| Anthropic: Claude Sonnet 4.5 | 37 | 1M | $3 / $15 | Thinking | Test it in the Studio |
| Anthropic: Claude Sonnet 4.5 (batch) | 37 | 1M | $1.5 / $7.5 | Thinking | Test it in the Studio |
| MoonshotAI: Kimi K2.5 | 36 | 262K | $0.6 / $3 | Thinking | Test it in the Studio |
| OpenAI: GPT-5 | 35 | 400K | $1.25 / $10 | Thinking | Test it in the Studio |
| OpenAI: GPT-5 (batch) | 35 | 400K | $0.63 / $5 | Thinking | Test it in the Studio |
ZZ.ai: GLM 4.7 | 35 | 205K | $0.4 / $1.75 | Thinking | Test it in the Studio |
| Qwen: Qwen3.5 397B A17B | 34 | 262K | $0.39 / $2.34 | Thinking | Test it in the Studio |
MMeituan: LongCat 2.0 | 34 | 1.0M | $0.3 / $1.2 | Thinking | Test it in the Studio |
KKwaipilot: KAT-Coder-Pro V2 | 34 | 262K | $0.3 / $1.2 | Test it in the Studio | |
| Qwen: Qwen3.5-122B-A10B | 33 | 262K | $0.26 / $2.08 | Thinking | Test it in the Studio |
| Qwen: Qwen3.6 35B A3B | 32 | 262K | $0.14 / $1 | Thinking | Test it in the Studio |
| DeepSeek: DeepSeek V3.1 Terminus | 31 | 164K | $0.27 / $1 | Thinking | Test it in the Studio |
SStepFun: Step 3.7 Flash | 31 | 262K | $0.2 / $1.15 | Thinking | Test it in the Studio |
MMistral: Mistral Medium 3.5 | 30 | 262K | $1.5 / $7.5 | Thinking | Test it in the Studio |
| Anthropic: Claude Haiku 4.5 | 30 | 200K | $1 / $5 | Thinking | Test it in the Studio |
| Anthropic: Claude Haiku 4.5 (batch) | 30 | 200K | $0.5 / $2.5 | Thinking | Test it in the Studio |
| Anthropic: Claude Sonnet 4 | 30 | 1M | $3 / $15 | Thinking | Test it in the Studio |
| Google: Gemma 4 31B | 30 | 262K | $0.09 / $0.34 | Thinking | Test it in the Studio |
| Google: Gemma 4 31B (free) | 30 | 262K | Thinking | Test it in the Studio | |
ZZ.ai: GLM 4.6 | 29 | 205K | $0.5 / $2 | Thinking | Test it in the Studio |
| Google: Gemma 4 26B A4B | 26 | 262K | $0.07 / $0.34 | Thinking | Test it in the Studio |
| Google: Gemma 4 26B A4B (free) | 26 | 262K | Thinking | Test it in the Studio | |
| Google: Gemini 2.5 Pro | 26 | 1.0M | $1.25 / $10 | Thinking | Test it in the Studio |
| Google: Gemini 2.5 Pro (batch) | 26 | 1.0M | $0.63 / $5 | Thinking | Test it in the Studio |
| OpenAI: GPT-5 Mini | 26 | 400K | $0.25 / $2 | Thinking | Test it in the Studio |
| OpenAI: GPT-5 Mini (batch) | 26 | 400K | $0.13 / $1 | Thinking | Test it in the Studio |
| NVIDIA: Nemotron 3 Super | 26 | 1M | $0.09 / $0.4 | Thinking | Test it in the Studio |
| NVIDIA: Nemotron 3 Super (free) | 26 | 262K | Thinking | Test it in the Studio | |
| Google: Gemini 3.1 Flash Lite Preview | 26 | 1.0M | $0.25 / $1.5 | Thinking | Test it in the Studio |
| Qwen: Qwen3.5-35B-A3B | 24 | 262K | $0.25 / $1.25 | Thinking | Test it in the Studio |
| OpenAI: gpt-oss-120b | 24 | 131K | $0.04 / $0.17 | Thinking | Test it in the Studio |
| NVIDIA: Nemotron 3.5 Lightning | 24 | 262K | $0.08 / $0.2 | Thinking | Test it in the Studio |
| NVIDIA: Nemotron 3.5 Lightning (free) | 24 | 1M | Thinking | Test it in the Studio | |
CCohere: Command A | 23 | 256K | $2.5 / $10 | Test it in the Studio | |
IInception: Mercury 2 | 22 | 128K | $0.25 / $0.75 | Thinking | Test it in the Studio |
| Qwen: Qwen3.5-9B | 22 | 262K | $0.1 / $0.15 | Thinking | Test it in the Studio |
| Qwen: Qwen3 Coder Next | 21 | 262K | $0.12 / $0.8 | Test it in the Studio | |
CCohere: North Mini Code (free) | 20 | 256K | Thinking | Test it in the Studio | |
| Qwen: Qwen3 235B A22B Thinking 2507 | 20 | 131K | $0.23 / $2.3 | Thinking | Test it in the Studio |
MMistral: Mistral Small 4 | 20 | 262K | $0.15 / $0.6 | Thinking | Test it in the Studio |
MMistral: Devstral 2 2512 | 19 | 262K | $0.44 / $2.2 | Test it in the Studio | |
AArcee AI: Trinity Large Thinking | 19 | 262K | $0.22 / $0.85 | Thinking | Test it in the Studio |
| DeepSeek: R1 | 19 | 64K | $0.7 / $2.5 | Thinking | Test it in the Studio |
| Qwen: Qwen3 Next 80B A3B Thinking | 17 | 262K | $0.15 / $1.2 | Thinking | Test it in the Studio |
MMistral: Mistral Large 3 2512 | 16 | 262K | $0.5 / $1.5 | Test it in the Studio | |
| OpenAI: o3 Mini High | 16 | 200K | $1.1 / $4.4 | Thinking | Test it in the Studio |
| OpenAI: o3 Mini High (batch) | 16 | 200K | $0.55 / $2.2 | Thinking | Test it in the Studio |
| OpenAI: gpt-oss-20b | 15 | 131K | $0.03 / $0.13 | Thinking | Test it in the Studio |
| DeepSeek: DeepSeek V3 0324 | 15 | 164K | $0.25 / $1 | Test it in the Studio | |
| OpenAI: GPT-4.1 Mini | 15 | 1.0M | $0.4 / $1.6 | Test it in the Studio | |
| OpenAI: GPT-4.1 Mini (batch) | 15 | 1.0M | $0.2 / $0.8 | Test it in the Studio | |
MMistral: Mistral Medium 3.1 | 15 | 131K | $0.4 / $2 | Test it in the Studio | |
| Qwen: Qwen3 30B A3B Thinking 2507 | 15 | 82K | $0.2 / $2.4 | Thinking | Test it in the Studio |
UUpstage: Solar Pro 3 | 15 | 131K | $0.15 / $0.6 | Thinking | Test it in the Studio |
| NVIDIA: Nemotron 3 Nano 30B A3B | 15 | 262K | $0.05 / $0.2 | Thinking | Test it in the Studio |
| Meta: Llama 4 Maverick | 15 | 1.0M | $0.2 / $0.8 | Test it in the Studio | |
| Qwen: Qwen3 32B | 11 | 131K | $0.08 / $0.28 | Thinking | Test it in the Studio |
MMistral: Ministral 3 14B 2512 | 11 | 262K | $0.2 / $0.2 | Test it in the Studio | |
| Qwen: Qwen3 14B | 10 | 131K | $0.12 / $0.24 | Thinking | Test it in the Studio |
| Meta: Llama 4 Scout | 10 | 1.3M | $0.11 / $0.34 | Test it in the Studio | |
| OpenAI: GPT-4.1 Nano | 10 | 1.0M | $0.1 / $0.4 | Test it in the Studio | |
| OpenAI: GPT-4.1 Nano (batch) | 10 | 1.0M | $0.05 / $0.2 | Test it in the Studio | |
MMistral: Ministral 3 8B 2512 | 9 | 262K | $0.15 / $0.15 | Test it in the Studio | |
| Qwen: Qwen3 8B | 8 | 131K | $0.12 / $0.45 | Thinking | Test it in the Studio |
| Google: Gemma 3 27B | 7 | 262K | $0.08 / $0.45 | Test it in the Studio | |
MMistral: Ministral 3 3B 2512 | 7 | 131K | $0.1 / $0.1 | Test it in the Studio | |
| Google: Gemma 3 12B | 6 | 131K | $0.05 / $0.15 | Test it in the Studio | |
IIBM: Granite 4.1 8B | 0 | 131K | $0.05 / $0.1 | Test it in the Studio | |
| NVIDIA: Nemotron 3 Nano Omni (free) | 0 | 256K | Thinking | Test it in the Studio | |
 Amazon: Nova 2 Lite | 0 | 1M | $0.3 / $2.5 | Thinking | Test it in the Studio |
| DeepSeek: DeepSeek V3.2 | 0 | 164K | $0.26 / $0.38 | Thinking | Test it in the Studio |
| MoonshotAI: Kimi K2 Thinking | 0 | 262K | $0.6 / $2.5 | Thinking | Test it in the Studio |
| Google: Gemma 3 4B | 0 | 131K | $0.05 / $0.1 | Test it in the Studio | |
| OpenAI: o1 | 0 | 200K | $15 / $60 | Thinking | Test it in the Studio |
| OpenAI: o1 (batch) | 0 | 200K | $7.5 / $30 | Thinking | Test it in the Studio |
| Meta: Llama 3.3 70B Instruct | 0 | 131K | $0.71 / $0.71 | Test it in the Studio | |
| Meta: Llama 3.1 8B Instruct | 0 | 131K | $0.05 / $0.08 | Test it in the Studio | |
| OpenAI: GPT-4o-mini | 0 | 128K | $0.15 / $0.6 | Test it in the Studio | |
| OpenAI: GPT-4o-mini (batch) | 0 | 128K | $0.08 / $0.3 | Test it in the Studio | |
| OpenAI: GPT-4o (2024-05-13) | 0 | 128K | $5 / $15 | Test it in the Studio | |
| Meta: Muse Spark 1.2 Contributor | 1.0M | $0.1 / $0.2 | Thinking | Test it in the Studio | |
| DeepSeek: DeepSeek V4 Flash Vision Exp | 1.0M | $0.44 / $1.32 | Thinking | Test it in the Studio | |
OOx Alpha | 1.0M | Thinking | Test it in the Studio | ||
TTencent: Hy-MT2-1.8B | 8K | $0.04 / $0.18 | Test it in the Studio | ||
TTencent: Hy-MT2-30B-A3B | 8K | $0.07 / $0.3 | Test it in the Studio | ||
ZZ.ai: GLM Latest | 1.0M | $1.4 / $4.4 | Thinking | Test it in the Studio | |
TTencent: Hy-MT2-7B | 8K | $0.07 / $0.3 | Test it in the Studio | ||
DDots Studio: Dots3-Note Preview (free) | 512K | Thinking | Test it in the Studio | ||
BByteDance Seed: Seed 2.1 Turbo | 262K | $0.5 / $2.5 | Thinking | Test it in the Studio | |
BByteDance Seed: Seed-2.0-Code | 262K | $0.5 / $3 | Thinking | Test it in the Studio | |
LLiquidAI: LFM2.5-2.6B (free) | 66K | Thinking | Test it in the Studio | ||
SSakana: Sakana Namazu | 262K | $0.95 / $4 | Thinking | Test it in the Studio | |
| Meta: Muse Glimmer 30B | 131K | $0.35 / $1.5 | Thinking | Test it in the Studio | |
| DeepSeek V4 Flash Latest | 1.3M | $0.03 / $0.08 | Thinking | Test it in the Studio | |
| Qwen: Qwen3.7 Flash | 1M | $0.03 / $0.13 | Thinking | Test it in the Studio | |
| Claude Opus 5 (Fast) | 1M | $10 / $50 | Thinking | Test it in the Studio | |
PPoolside: Laguna S 2.1 | 1.0M | $0.09 / $0.18 | Thinking | Test it in the Studio | |
PPoolside: Laguna S 2.1 (free) | 262K | Thinking | Test it in the Studio | ||
AAuto Router (Beta) | 2M | Test it in the Studio | |||
KKwaipilot: KAT-Coder-Air V2.5 | 256K | $0.15 / $0.6 | Test it in the Studio | ||
KKwaipilot: KAT-Coder-Pro V2.5 | 256K | $0.74 / $2.96 | Test it in the Studio | ||
| OpenAI: GPT-5.6 Luna Pro | 1.1M | $0.2 / $1.2 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5.6 Luna Pro (batch) | 1.1M | $0.1 / $0.6 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5.6 Terra Pro | 1.1M | $2 / $12 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5.6 Terra Pro (batch) | 1.1M | $1 / $6 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5.6 Sol Pro | 1.1M | $2 / $10 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5.6 Sol Pro (batch) | 1.1M | $1 / $5 | Thinking | Test it in the Studio | |
| xAI: Grok Latest | 500K | $2 / $6 | Thinking | Test it in the Studio | |
AAionLabs: Aion-3.0-Mini | 131K | $0.7 / $1.4 | Thinking | Test it in the Studio | |
AAionLabs: Aion-3.0 | 131K | $3 / $6 | Thinking | Test it in the Studio | |
TTencent: Hy3 | 262K | $0.13 / $0.53 | Thinking | Test it in the Studio | |
PPoolside: Laguna XS 2.1 | 262K | $0.06 / $0.12 | Thinking | Test it in the Studio | |
PPoolside: Laguna XS 2.1 (free) | 262K | Thinking | Test it in the Studio | ||
| Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | 66K | $0.25 / $1.5 | Thinking | Test it in the Studio | |
NNex AGI: Nex-N2-Mini | 262K | $0.03 / $0.1 | Thinking | Test it in the Studio | |
SSakana: Fugu Ultra | 1M | $5 / $30 | Thinking | Test it in the Studio | |
| Google: Nano Banana 2 (Gemini 3.1 Flash Image) | 131K | $0.5 / $3 | Thinking | Test it in the Studio | |
| Google: Nano Banana Pro (Gemini 3 Pro Image) | 131K | $2 / $12 | Thinking | Test it in the Studio | |
OOpenRouter: Fusion | 1M | Test it in the Studio | |||
| Anthropic: Claude Fable Latest | 1M | $10 / $50 | Thinking | Test it in the Studio | |
| NVIDIA: Nemotron 3.5 Content Safety (free) | 128K | Thinking | Test it in the Studio | ||
| Anthropic: Claude Opus 4.8 (Fast) | 1M | $10 / $50 | Thinking | Test it in the Studio | |
| Anthropic: Claude Opus 4.7 (Fast) | 1M | $30 / $150 | Thinking | Test it in the Studio | |
PPerceptron: Perceptron Mk1 | 33K | $0.15 / $1.5 | Thinking | Test it in the Studio | |
| Google: Gemini 3.1 Flash Lite | 1.0M | $0.25 / $1.5 | Thinking | Test it in the Studio | |
| Google: Gemini 3.1 Flash Lite (batch) | 1.0M | $0.13 / $0.75 | Thinking | Test it in the Studio | |
| OpenAI: GPT Chat Latest | 400K | $5 / $30 | Test it in the Studio | ||
| Anthropic Claude Haiku Latest | 200K | $1 / $5 | Thinking | Test it in the Studio | |
| OpenAI GPT Mini Latest | 400K | $0.75 / $4.5 | Thinking | Test it in the Studio | |
| Google Gemini Pro Latest | 1.0M | $2 / $12 | Thinking | Test it in the Studio | |
| MoonshotAI Kimi Latest | 1.0M | $2.55 / $12.75 | Thinking | Test it in the Studio | |
| Google Gemini Flash Latest | 1.0M | $0.38 / $1.88 | Thinking | Test it in the Studio | |
| Anthropic Claude Sonnet Latest | 1M | $2 / $10 | Thinking | Test it in the Studio | |
| OpenAI GPT Latest | 1.1M | $2 / $10 | Thinking | Test it in the Studio | |
| Qwen: Qwen3.5 Plus 2026-04-20 | 1M | $0.3 / $1.8 | Thinking | Test it in the Studio | |
| Qwen: Qwen3.6 Flash | 1M | $0.19 / $1.13 | Thinking | Test it in the Studio | |
| Qwen: Qwen3.6 Max Preview | 262K | $1.03 / $6.16 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5.5 Pro | 1.1M | $30 / $180 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5.5 Pro (batch) | 1.1M | $15 / $90 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5.4 Image 2 | 272K | $8 / $15 | Thinking | Test it in the Studio | |
| Anthropic: Claude Opus Latest | 1M | $5 / $25 | Thinking | Test it in the Studio | |
PPareto Code Router | 2M | Test it in the Studio | |||
ZZ.ai: GLM 5V Turbo | 203K | $1.2 / $4 | Thinking | Test it in the Studio | |
| SpaceXAI: Grok 4.20 Multi-Agent | 2M | $1.25 / $2.5 | Thinking | Test it in the Studio | |
| SpaceXAI: Grok 4.20 | 2M | $1.25 / $2.5 | Thinking | Test it in the Studio | |
| Google: Lyria 3 Pro Preview | 1.0M | Test it in the Studio | |||
| Google: Lyria 3 Clip Preview | 1.0M | Test it in the Studio | |||
RReka Edge | 16K | $0.1 / $0.1 | Thinking | Test it in the Studio | |
ZZ.ai: GLM 5 Turbo | 203K | $1.2 / $4 | Thinking | Test it in the Studio | |
BByteDance Seed: Seed-2.0-Lite | 262K | $0.25 / $2 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5.4 Pro | 1.1M | $30 / $180 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5.4 Pro (batch) | 1.1M | $15 / $90 | Thinking | Test it in the Studio | |
BByteDance Seed: Seed-2.0-Mini | 262K | $0.1 / $0.4 | Thinking | Test it in the Studio | |
| Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) | 66K | $0.5 / $3 | Thinking | Test it in the Studio | |
| Qwen: Qwen3.5-27B | 262K | $0.2 / $1.56 | Thinking | Test it in the Studio | |
| Qwen: Qwen3.5-Flash | 1M | $0.07 / $0.26 | Thinking | Test it in the Studio | |
| Google: Gemini 3.1 Pro Preview Custom Tools | 1.0M | $2 / $12 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5.3-Codex | 400K | $1.75 / $14 | Thinking | Test it in the Studio | |
AAionLabs: Aion-2.0 | 131K | $0.8 / $1.6 | Thinking | Test it in the Studio | |
| Qwen: Qwen3.5 Plus 2026-02-15 | 1M | $0.26 / $1.56 | Thinking | Test it in the Studio | |
MMiniMax: MiniMax M2.5 | 205K | $0.27 / $1.08 | Thinking | Test it in the Studio | |
ZZ.ai: GLM 5 | 205K | $0.6 / $1.92 | Thinking | Test it in the Studio | |
| Qwen: Qwen3 Max Thinking | 262K | $0.78 / $3.9 | Thinking | Test it in the Studio | |
| Anthropic: Claude Opus 4.6 | 1M | $5 / $25 | Thinking | Test it in the Studio | |
| Anthropic: Claude Opus 4.6 (batch) | 1M | $2.5 / $12.5 | Thinking | Test it in the Studio | |
FFree Models Router | 200K | Test it in the Studio | |||
SStepFun: Step 3.5 Flash | 262K | $0.1 / $0.3 | Thinking | Test it in the Studio | |
MMiniMax: MiniMax M2-her | 66K | $0.3 / $1.2 | Test it in the Studio | ||
WWriter: Palmyra X5 | 1.0M | $0.6 / $6 | Test it in the Studio | ||
| OpenAI: GPT Audio | 128K | $2.5 / $10 | Test it in the Studio | ||
| OpenAI: GPT Audio Mini | 128K | $0.6 / $2.4 | Test it in the Studio | ||
ZZ.ai: GLM 4.7 Flash | 203K | $0.06 / $0.4 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5.2-Codex | 400K | $1.75 / $14 | Thinking | Test it in the Studio | |
BByteDance Seed: Seed 1.6 Flash | 262K | $0.08 / $0.3 | Thinking | Test it in the Studio | |
BByteDance Seed: Seed 1.6 | 262K | $0.25 / $2 | Thinking | Test it in the Studio | |
MMiniMax: MiniMax M2.1 | 205K | $0.3 / $1.2 | Thinking | Test it in the Studio | |
| Google: Gemini 3 Flash Preview | 1.0M | $0.5 / $3 | Thinking | Test it in the Studio | |
| Google: Gemini 3 Flash Preview (batch) | 1.0M | $0.25 / $1.5 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5.2 Chat | 128K | $1.75 / $14 | Test it in the Studio | ||
| OpenAI: GPT-5.2 Pro | 400K | $21 / $168 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5.2 Pro (batch) | 400K | $10.5 / $84 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5.2 | 400K | $1.75 / $14 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5.2 (batch) | 400K | $0.88 / $7 | Thinking | Test it in the Studio | |
RRelace: Relace Search | 256K | $1 / $3 | Test it in the Studio | ||
ZZ.ai: GLM 4.6V | 131K | $0.3 / $0.9 | Thinking | Test it in the Studio | |
BBody Builder (beta) | 128K | Test it in the Studio | |||
| OpenAI: GPT-5.1-Codex-Max | 400K | $1.25 / $10 | Thinking | Test it in the Studio | |
| Anthropic: Claude Opus 4.5 | 200K | $5 / $25 | Thinking | Test it in the Studio | |
| Anthropic: Claude Opus 4.5 (batch) | 200K | $2.5 / $12.5 | Thinking | Test it in the Studio | |
AAllenAI: Olmo 3 32B Think | 66K | $0.15 / $0.5 | Thinking | Test it in the Studio | |
| Google: Nano Banana Pro (Gemini 3 Pro Image Preview) | 66K | $2 / $12 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5.1-Codex | 400K | $1.25 / $10 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5.1-Codex-Mini | 400K | $0.25 / $2 | Thinking | Test it in the Studio | |
| Amazon: Nova Premier 1.0 | 1M | $2.5 / $12.5 | Test it in the Studio | ||
PPerplexity: Sonar Pro Search | 200K | $3 / $15 | Thinking | Test it in the Studio | |
MMistral: Voxtral Small 24B 2507 | 32K | $0.1 / $0.3 | Test it in the Studio | ||
| OpenAI: gpt-oss-safeguard-20b | 131K | $0.08 / $0.3 | Thinking | Test it in the Studio | |
MMiniMax: MiniMax M2 | 205K | $0.26 / $1.02 | Thinking | Test it in the Studio | |
| Qwen: Qwen3 VL 32B Instruct | 131K | $0.1 / $0.42 | Test it in the Studio | ||
IIBM: Granite 4.0 Micro | 131K | $0.02 / $0.11 | Test it in the Studio | ||
| OpenAI: GPT-5 Image Mini | 400K | $2.5 / $2 | Thinking | Test it in the Studio | |
| Qwen: Qwen3 VL 8B Thinking | 131K | $0.18 / $2.1 | Thinking | Test it in the Studio | |
| Qwen: Qwen3 VL 8B Instruct | 262K | $0.12 / $0.45 | Test it in the Studio | ||
| OpenAI: GPT-5 Image | 400K | $10 / $10 | Thinking | Test it in the Studio | |
| Google: Nano Banana (Gemini 2.5 Flash Image) | 33K | $0.3 / $2.5 | Test it in the Studio | ||
| Qwen: Qwen3 VL 30B A3B Thinking | 262K | $0.2 / $2.4 | Thinking | Test it in the Studio | |
| Qwen: Qwen3 VL 30B A3B Instruct | 262K | $0.13 / $0.52 | Test it in the Studio | ||
| OpenAI: GPT-5 Pro | 400K | $15 / $120 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5 Pro (batch) | 400K | $7.5 / $60 | Thinking | Test it in the Studio | |
| DeepSeek: DeepSeek V3.2 Exp | 164K | $0.27 / $0.41 | Thinking | Test it in the Studio | |
TTheDrummer: Cydonia 24B V4.1 | 131K | $0.3 / $0.5 | Test it in the Studio | ||
RRelace: Relace Apply 3 | 256K | $0.85 / $1.25 | Test it in the Studio | ||
| Qwen: Qwen3 VL 235B A22B Thinking | 131K | $0.4 / $4 | Thinking | Test it in the Studio | |
| Qwen: Qwen3 VL 235B A22B Instruct | 262K | $0.21 / $1.9 | Test it in the Studio | ||
| Qwen: Qwen3 Max | 262K | $0.78 / $3.9 | Thinking | Test it in the Studio | |
| Qwen: Qwen3 Coder Plus | 1M | $0.65 / $3.25 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5 Codex (batch) | 400K | $0.63 / $5 | Thinking | Test it in the Studio | |
| Qwen: Qwen3 Coder Flash | 1M | $0.2 / $0.98 | Test it in the Studio | ||
| Qwen: Qwen3 Next 80B A3B Instruct | 262K | $0.1 / $1.1 | Test it in the Studio | ||
| Qwen: Qwen Plus 0728 | 1M | $0.26 / $0.78 | Thinking | Test it in the Studio | |
| MoonshotAI: Kimi K2 0905 | 262K | $0.6 / $2.5 | Test it in the Studio | ||
NNous: Hermes 4 70B | 131K | $0.13 / $0.4 | Thinking | Test it in the Studio | |
NNous: Hermes 4 405B | 131K | $1 / $3 | Thinking | Test it in the Studio | |
| DeepSeek: DeepSeek V3.1 | 164K | $0.55 / $1.65 | Thinking | Test it in the Studio | |
ZZ.ai: GLM 4.5V | 66K | $0.6 / $1.8 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5 Nano | 400K | $0.05 / $0.4 | Thinking | Test it in the Studio | |
| OpenAI: GPT-5 Nano (batch) | 400K | $0.03 / $0.2 | Thinking | Test it in the Studio | |
| Anthropic: Claude Opus 4.1 | 200K | $15 / $75 | Thinking | Test it in the Studio | |
| Anthropic: Claude Opus 4.1 (batch) | 200K | $7.5 / $37.5 | Thinking | Test it in the Studio | |
MMistral: Codestral 2508 | 256K | $0.3 / $0.9 | Test it in the Studio | ||
| Qwen: Qwen3 Coder 30B A3B Instruct | 262K | $0.07 / $0.28 | Test it in the Studio | ||
| Qwen: Qwen3 30B A3B Instruct 2507 | 262K | $0.05 / $0.19 | Test it in the Studio | ||
ZZ.ai: GLM 4.5 | 131K | $0.6 / $2.2 | Thinking | Test it in the Studio | |
ZZ.ai: GLM 4.5 Air | 131K | $0.13 / $0.85 | Thinking | Test it in the Studio | |
| Qwen: Qwen3 Coder 480B A35B | 262K | $0.3 / $1 | Test it in the Studio | ||
BByteDance: UI-TARS 7B | 128K | $0.1 / $0.2 | Test it in the Studio | ||
| Google: Gemini 2.5 Flash Lite | 1.0M | $0.1 / $0.4 | Thinking | Test it in the Studio | |
| Google: Gemini 2.5 Flash Lite (batch) | 1.0M | $0.05 / $0.2 | Thinking | Test it in the Studio | |
| Qwen: Qwen3 235B A22B Instruct 2507 | 262K | $0.09 / $0.55 | Test it in the Studio | ||
| MoonshotAI: Kimi K2 0711 | 131K | $0.57 / $2.3 | Test it in the Studio | ||
VVenice: Uncensored | 128K | $0.2 / $0.9 | Test it in the Studio | ||
TTencent: Hunyuan A13B Instruct | 131K | $0.14 / $0.57 | Thinking | Test it in the Studio | |
MMorph: Morph V3 Large | 262K | $0.9 / $1.9 | Test it in the Studio | ||
MMorph: Morph V3 Fast | 82K | $0.8 / $1.2 | Test it in the Studio | ||
BBaidu: ERNIE 4.5 VL 424B A47B | 123K | $0.42 / $1.25 | Thinking | Test it in the Studio | |
MMistral: Mistral Small 3.2 24B | 131K | $0.08 / $0.2 | Test it in the Studio | ||
MMiniMax: MiniMax M1 | 1M | $0.55 / $2.2 | Thinking | Test it in the Studio | |
| Google: Gemini 2.5 Flash | 1.0M | $0.3 / $2.5 | Thinking | Test it in the Studio | |
| Google: Gemini 2.5 Flash (batch) | 1.0M | $0.15 / $1.25 | Thinking | Test it in the Studio | |
| OpenAI: o3 Pro | 200K | $20 / $80 | Thinking | Test it in the Studio | |
| OpenAI: o3 Pro (batch) | 200K | $10 / $40 | Thinking | Test it in the Studio | |
| Google: Gemini 2.5 Pro Preview 06-05 | 1.0M | $1.25 / $10 | Thinking | Test it in the Studio | |
| DeepSeek: R1 0528 | 164K | $0.5 / $2.15 | Thinking | Test it in the Studio | |
| Anthropic: Claude Opus 4 | 200K | $15 / $75 | Thinking | Test it in the Studio | |
MMistral: Mistral Medium 3 | 131K | $0.4 / $2 | Test it in the Studio | ||
| Google: Gemini 2.5 Pro Preview 05-06 | 1.0M | $1.25 / $10 | Thinking | Test it in the Studio | |
AArcee AI: Virtuoso Large | 131K | $0.75 / $1.2 | Test it in the Studio | ||
| Meta: Llama Guard 4 12B | 164K | $0.18 / $0.18 | Test it in the Studio | ||
| Qwen: Qwen3 30B A3B | 131K | $0.12 / $0.5 | Thinking | Test it in the Studio | |
| Qwen: Qwen3 235B A22B | 131K | $0.45 / $1.82 | Thinking | Test it in the Studio | |
| OpenAI: o4 Mini High | 200K | $1.1 / $4.4 | Thinking | Test it in the Studio | |
| OpenAI: o4 Mini High (batch) | 200K | $0.55 / $2.2 | Thinking | Test it in the Studio | |
| OpenAI: o3 | 200K | $2 / $8 | Thinking | Test it in the Studio | |
| OpenAI: o3 (batch) | 200K | $1 / $4 | Thinking | Test it in the Studio | |
| OpenAI: o4 Mini | 200K | $1.1 / $4.4 | Thinking | Test it in the Studio | |
| OpenAI: o4 Mini (batch) | 200K | $0.55 / $2.2 | Thinking | Test it in the Studio | |
| OpenAI: GPT-4.1 | 1.0M | $2 / $8 | Test it in the Studio | ||
| OpenAI: GPT-4.1 (batch) | 1.0M | $1 / $4 | Test it in the Studio | ||
| OpenAI: o1-pro | 200K | $150 / $600 | Thinking | Test it in the Studio | |
| OpenAI: o1-pro (batch) | 200K | $75 / $300 | Thinking | Test it in the Studio | |
MMistral: Mistral Small 3.1 24B | 128K | $0.35 / $0.55 | Test it in the Studio | ||
RReka Flash 3 | 66K | $0.1 / $0.2 | Thinking | Test it in the Studio | |
TTheDrummer: Skyfall 36B V2 | 33K | $0.55 / $0.8 | Test it in the Studio | ||
PPerplexity: Sonar Reasoning Pro | 128K | $2 / $8 | Thinking | Test it in the Studio | |
PPerplexity: Sonar Pro | 200K | $3 / $15 | Test it in the Studio | ||
PPerplexity: Sonar Deep Research | 128K | $2 / $8 | Thinking | Test it in the Studio | |
MMistral: Saba | 33K | $0.2 / $0.6 | Test it in the Studio | ||
AAionLabs: Aion-RP 1.0 (8B) | 33K | $0.8 / $1.6 | Test it in the Studio | ||
| Qwen: Qwen2.5 VL 72B Instruct | 128K | $0.25 / $0.75 | Test it in the Studio | ||
| Qwen: Qwen-Plus | 1M | $0.26 / $0.78 | Test it in the Studio | ||
| OpenAI: o3 Mini | 200K | $1.1 / $4.4 | Thinking | Test it in the Studio | |
| OpenAI: o3 Mini (batch) | 200K | $0.55 / $2.2 | Thinking | Test it in the Studio | |
MMistral: Mistral Small 3 | 33K | $0.05 / $0.08 | Test it in the Studio | ||
PPerplexity: Sonar | 127K | $1 / $1 | Test it in the Studio | ||
| DeepSeek: R1 Distill Llama 70B | 8K | $0.8 / $0.8 | Thinking | Test it in the Studio | |
MMiniMax: MiniMax-01 | 1.0M | $0.2 / $1.1 | Test it in the Studio | ||
 Microsoft: Phi 4 | 16K | $0.07 / $0.14 | Test it in the Studio | ||
| DeepSeek: DeepSeek V3 | 164K | $0.26 / $1.03 | Test it in the Studio | ||
SSao10K: Llama 3.3 Euryale 70B | 131K | $0.65 / $0.75 | Test it in the Studio | ||
CCohere: Command R7B (12-2024) | 128K | $0.04 / $0.15 | Test it in the Studio | ||
| Amazon: Nova Lite 1.0 | 300K | $0.06 / $0.24 | Test it in the Studio | ||
| Amazon: Nova Micro 1.0 | 128K | $0.04 / $0.14 | Test it in the Studio | ||
| Amazon: Nova Pro 1.0 | 300K | $0.8 / $3.2 | Test it in the Studio | ||
| OpenAI: GPT-4o (2024-11-20) | 128K | $2.5 / $10 | Test it in the Studio | ||
MMistral Large 2407 | 131K | $2 / $6 | Test it in the Studio | ||
| Qwen2.5 Coder 32B Instruct | 33K | $0.66 / $1 | Test it in the Studio | ||
TTheDrummer: UnslopNemo 12B | 1.0M | $0.4 / $0.4 | Test it in the Studio | ||
MMagnum v4 72B | 33K | $3 / $5 | Test it in the Studio | ||
MMistral: Ministral 8B | 128K | $0.11 / $0.11 | Test it in the Studio | ||
| Qwen: Qwen2.5 7B Instruct | 33K | $0.1 / $0.2 | Test it in the Studio | ||
TTheDrummer: Rocinante 12B | 66K | $0.25 / $0.5 | Test it in the Studio | ||
| Meta: Llama 3.2 1B Instruct | 60K | $0.03 / $0.2 | Test it in the Studio | ||
| Meta: Llama 3.2 3B Instruct | 131K | $0.05 / $0.33 | Test it in the Studio | ||
| Qwen2.5 72B Instruct | 33K | $0.36 / $0.4 | Test it in the Studio | ||
CCohere: Command R (08-2024) | 128K | $0.15 / $0.6 | Test it in the Studio | ||
CCohere: Command R+ (08-2024) | 128K | $2.5 / $10 | Test it in the Studio | ||
SSao10K: Llama 3.1 Euryale 70B v2.2 | 131K | $0.85 / $0.85 | Test it in the Studio | ||
NNous: Hermes 3 70B Instruct | 131K | $0.7 / $0.7 | Test it in the Studio | ||
NNous: Hermes 3 405B Instruct | 131K | $1 / $1 | Test it in the Studio | ||
SSao10K: Llama 3 8B Lunaris | 8K | $0.04 / $0.05 | Test it in the Studio | ||
| OpenAI: GPT-4o (2024-08-06) | 128K | $2.5 / $10 | Test it in the Studio | ||
| Meta: Llama 3.1 70B Instruct | 131K | $0.4 / $0.4 | Test it in the Studio | ||
MMistral: Mistral Nemo | 131K | $0.02 / $0.03 | Test it in the Studio | ||
| OpenAI: GPT-4o-mini (2024-07-18) | 128K | $0.15 / $0.6 | Test it in the Studio | ||
| Google: Gemma 2 27B | 8K | $0.65 / $0.65 | Test it in the Studio | ||
| OpenAI: GPT-4o | 128K | $2.5 / $10 | Test it in the Studio | ||
| OpenAI: GPT-4o (batch) | 128K | $1.25 / $5 | Test it in the Studio | ||
Qwen3.6 27B
+0 net
100%
Qwen3.6 27B
0%
Qwen3.6 27B
100%
Qwen3.6 27B
Verified scores are credibility-weighted (Bayesian shrinkage by sample count) and every published run is re-verifiable via its attestation hash · updates live.
