Compare AI models
Head-to-head scores for professional work, cost and speed.
ChatGPT vs Claude
GPT-6 Astra · Claude Opus 5.56 tasks side by side56.9Index58.4ChatGPT vs Gemini
GPT-6 Astra · Gemini 4 Carbon6 tasks side by side56.9Index59.4Claude vs Gemini
Claude Opus 5.5 · Gemini 4 Carbon6 tasks side by side58.4Index59.4Grok vs ChatGPT
Grok 4.7 · GPT-6 Astra35.3Index56.9DeepSeek vs ChatGPT
DeepSeek V4.1 Flash 1017 · GPT-6 Astra6 tasks side by side32.5Index56.9Grok vs Claude
Grok 4.7 · Claude Opus 5.535.3Index58.4Grok vs Gemini
Grok 4.7 · Gemini 4 Carbon35.3Index59.4DeepSeek vs Claude
DeepSeek V4.1 Flash 1017 · Claude Opus 5.56 tasks side by side32.5Index58.4DeepSeek vs Gemini
DeepSeek V4.1 Flash 1017 · Gemini 4 Carbon6 tasks side by side32.5Index59.4Kimi vs Claude
Kimi K3.1 Pro · Claude Opus 5.546.0Index58.4Qwen vs DeepSeek
Qwen3.8 Max · DeepSeek V4.1 Flash 101733.6Index32.5Meta AI vs ChatGPT
Muse Wonder Full · GPT-6 Astra49.7Index56.9Mistral vs ChatGPT
Mistral Large 4 · GPT-6 Astra26.0Index56.9GLM vs Claude
GLM-5.3 · Claude Opus 5.531.7Index58.4Claude Opus 5.5 vs GPT-6 Astra
Claude Opus 5.5 · GPT-6 Astra6 tasks side by side58.4Index56.9Gemini 4 Carbon vs Claude Opus 5.5
Gemini 4 Carbon · Claude Opus 5.559.4Index58.4Gemini 4 Carbon vs GPT-6 Astra
Gemini 4 Carbon · GPT-6 Astra59.4Index56.9Claude Opus 5.5 vs Claude Sonnet 5.5
Claude Opus 5.5 · Claude Sonnet 5.558.4Index54.2Claude Sonnet 5.5 vs GPT-6.1 Sol
Claude Sonnet 5.5 · GPT-6.1 Sol54.2Index54.5GPT-6.1 Sol vs GPT-6 Astra
GPT-6.1 Sol · GPT-6 Astra54.5Index56.9All measured models
28| Rank | Model and setting | Intelligence Index | Price in / out | Tokens/s |
|---|---|---|---|---|
| 1 | Gemini 4 Carbon (High)Google · Limited early access | 59.4 | $4 / $20 | 94 |
| 2 | Claude Opus 5.5 (Max, Default Fallback)Anthropic | 58.4 | $4 / $20 | 96 |
| 3 | GPT-6 Astra (Max)OpenAI | 56.9 | $10 / $50 | 73 |
| 4 | GPT-6.1 Sol (Max)OpenAI | 54.5 | $2 / $10 | 93 |
| 5 | Claude Sonnet 5.5 (Max, Default Fallback)Anthropic | 54.2 | $2 / $10 | 140 |
| 6 | GPT-6.1 Terra (Max)OpenAI | 51.0 | $1 / $5 | 110 |
| 7 | Muse Wonder Full (Max)Meta | 49.7 | — | — |
| 8 | Claude Fable 5.1 (Max, Default Fallback)Anthropic | 49.0 | $10 / $50 | 70 |
| 9 | Kimi K3.1 ProKimi | 46.0 | $2 / $10 | 31 |
| 10 | Muse Wonder (Max)Meta | 43.3 | $4 / $20 | 200 |
| 11 | Claude Haiku 5.5 (Max)Anthropic | 36.2 | $0.10 / $0.50 | 235 |
| 12 | Grok 4.7 (Xhigh)SpaceXAI | 35.3 | $2 / $6 | 86 |
| 13 | Qwen3.8 Max (0902)Alibaba | 33.6 | $2 / $6 | 38 |
| 14 | DeepSeek V4.1 Flash 1017 (Max)DeepSeek · Open weights | 32.5 | $0.30 / $1.20 | 174 |
| 15 | GLM-5.3 (Max)Z AI · Open weights | 31.7 | $1.40 / $4.40 | 89 |
| 16 | Gemini 3.8 Flash (High)Google | 30.5 | $0.75 / $3.75 | 137 |
| 17 | MiMo-V2.6-ProXiaomi · Open weights | 29.9 | $0.43 / $0.87 | 44 |
| 18 | Ling 3.1 Flash 1019InclusionAI · Open weights | 29.5 | $0.30 / $0.90 | — |
| 19 | MiniMax-M3.1-FlashMiniMax · Open weights | 28.9 | $0.15 / $0.60 | 124 |
| 20 | Step 5 PreviewStepFun · Open weights | 28.5 | $1 / $2.70 | 143 |
| 21 | GPT-6 Luna (Max)OpenAI | 27.8 | $0.10 / $0.50 | 117 |
| 22 | Mistral Large 4 (High)Mistral · Open weights | 26.0 | $0.70 / $2.10 | — |
| 23 | Muse Spark Open (Xhigh)Meta · Open weights | 24.7 | $1.25 / $4.25 | 193 |
| 24 | Qwen3.8 27B (Xhigh)Alibaba · Open weights | 20.1 | $0.50 / $3 | 40 |
| 25 | K2 Horizon 375B A23BInstitute of Foundation Models · Open weights | 17.8 | $0.00 / $0.00 | 665 |
| 26 | Beam 1.0Reflection · Open weights | 17.7 | $0.40 / $1.20 | 369 |
| 27 | Nemotron 3.5 Super VLNVIDIA · Open weights | 13.6 | $0.20 / $0.50 | 468 |
| 28 | Inkling (Xhigh)Thinking Machines · Open weights | 12.5 | $1 / $4.05 | 215 |
Scores, prices and speeds: Artificial Analysis, independently measured, checked Nov 3, 2026. Model names include the tested reasoning setting. Stubbi has not rerun these evaluations. Consumer apps such as ChatGPT, Claude and Gemini may use other models and add features like search and memory.