Model rankings
1512 models · 5 boards · 2 sources
Smartest
Best open model
Best value
Best from China
Top three by Intelligence
GPT-6 Astra (max)OpenAI52.7
Claude Opus 5 (Adaptive Reasoning, Max Effort)Anthropic50.8
Top three open models
GLM-5.3 (max)Z AI · #8 overall44.8
Kimi K3 (max)Kimi · #11 overall43.6
GLM 5.3 FlashZ AI · #13 overall41.8
This week's changes
claude-opus-5.5-maxCoding · #1New
Gemini 3.8 Flash TTSSpeech · #2New
Grok Imagine Image 2.0Image · #4New
gpt-6-sol-maxCoding · #5New
Gemini 3.8 Flash-Lite TTSSpeech · #6New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)ClosedAnthropic · 4 more variants | 53.4 | $20 | 69 | 242 s |
| 2 | — | GPT-6 Astra (max)ClosedOpenAI · 4 more variants | 52.7 | $20 | 69 | 258 s |
| 3 | — | Claude Opus 5 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 4 more variants | 50.8 | $10 | 61 | 54 s |
| 4 | — | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)ClosedAnthropic | 49.6 | $20 | 65 | 108 s |
| 5 | — | Muse Spark 1.3 (max)ClosedMeta · 1 more variant | 48.1 | $2.0 | 241 | 24 s |
| 6 | — | GPT-5.6 Sol (max)ClosedOpenAI · 5 more variants | 47.0 | $8.0 | 69 | 119 s |
| 7 | — | GPT-5.6 Terra (max)ClosedOpenAI · 5 more variants | 42.1 | $4.5 | 101 | 200 s |
| 8 | — | Claude Opus 4.8 (Adaptive Reasoning, Max Effort)ClosedAnthropic | 41.8 | $10 | 58 | 28 s |
| 9 | — | Gemini 3.8 Flash (high)ClosedGoogle · 2 more variants | 40.9 | $1.5 | 331 | 26 s |
| 10 | — | Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant | 40.7 | $10 | 51 | 24 s |
| 11 | ▲ 1 | Gemini 3.7 Flash (medium)ClosedGoogle · 2 more variants | 39.6 | $1.5 | 303 | 4.9 s |
| 12 | ▼ 1 | Muse Spark 1.2 (xhigh)ClosedMeta | 39.6 | $2.0 | 234 | 14 s |
| 13 | — | GPT-5.4 (xhigh)ClosedOpenAI · 2 more variants | 39.0 | $5.6 | 140 | 144 s |
| 14 | — | GPT-5.5 (xhigh)ClosedOpenAI · 4 more variants | 38.4 | $11 | 111 | 65 s |
| 15 | — | Claude Sonnet 5 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 5 more variants | 38.2 | $4.0 | 76 | 132 s |
| 16 | — | GPT-5.6 Luna (max)ClosedOpenAI · 5 more variants | 37.3 | $0.45 | 167 | 127 s |
| 17 | — | Gemini 3.6 Flash (high)ClosedGoogle | 34.0 | $1.5 | 223 | 33 s |
| 18 | — | Muse Spark 1.1 (xhigh)ClosedMeta | 33.7 | $2.0 | — | — |
| 19 | — | Gemini 3.5 Flash (medium)ClosedGoogle · 2 more variants | 33.6 | $3.4 | 243 | 18 s |
| 20 | — | GPT-5.3 Codex (xhigh)ClosedOpenAI | 32.5 | $4.8 | 175 | 73 s |
| 21 | — | Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant | 31.9 | $10 | 41 | 22 s |
| 22 | — | Muse SparkClosedMeta | 31.3 | — | — | — |
| 23 | ▲ 1 | GPT-5.2 (xhigh)ClosedOpenAI · 2 more variants | 30.4 | $4.8 | 93 | 141 s |
| 24 | ▼ 1 | Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 2 more variants | 30.1 | $6.0 | 42 | 152 s |
| 25 | — | Gemini 3.1 Pro PreviewClosedGoogle | 29.7 | $4.5 | 124 | 64 s |
| 26 | — | Claude Opus 4.5 (Reasoning)ClosedAnthropic · 1 more variant | 29.1 | $10 | 48 | 12 s |
| 27 | — | GPT-5.2 Codex (xhigh)ClosedOpenAI | 28.5 | $4.8 | — | — |
| 28 | — | Gemini 3 Pro Preview (high)ClosedGoogle · 1 more variant | 28.0 | $4.5 | — | — |
| 29 | ▲ 1 | Gemini 3 Flash Preview (Reasoning)ClosedGoogle · 1 more variant | 26.3 | $1.1 | 219 | 5.5 s |
| 30 | ▼ 1 | GPT-5.5 Instant (June 2026)ClosedOpenAI · 1 more variant | 26.0 | $11 | 157 | 1.1 s |
| 31 | — | GPT-5 Codex (high)ClosedOpenAI | 24.9 | $3.4 | — | — |
| 32 | — | GPT-5.1 (high)ClosedOpenAI · 1 more variant | 24.7 | $3.4 | 132 | 27 s |
| 33 | — | GPT-5.4 mini (xhigh)ClosedOpenAI · 2 more variants | 24.1 | $1.7 | 245 | 93 s |
| 34 | — | GPT-5.1 Codex (high)ClosedOpenAI | 23.7 | $3.4 | — | — |
| 35 | — | GPT-5 (high)ClosedOpenAI · 4 more variants | 23.0 | $3.4 | 108 | 57 s |
| 36 | — | Claude 4.1 Opus (Reasoning)ClosedAnthropic · 1 more variant | 22.8 | $30 | — | — |
| 37 | — | Gemini 3.5 Flash-LiteClosedGoogle | 22.2 | $0.85 | 409 | 10 s |
| 38 | — | o3-proClosedOpenAI | 21.9 | $35 | — | — |
| 39 | — | GPT-5.4 nano (xhigh)ClosedOpenAI · 2 more variants | 20.7 | $0.46 | 186 | 74 s |
| 40 | — | Claude 4.5 Sonnet (Reasoning)ClosedAnthropic · 1 more variant | 20.7 | $6.0 | 42 | 11 s |
| 41 | — | Claude 4 Opus (Reasoning)ClosedAnthropic · 1 more variant | 20.6 | $30 | — | — |
| 42 | — | GPT-5 mini (medium)ClosedOpenAI · 2 more variants | 20.6 | $0.69 | 103 | 13 s |
| 43 | — | GPT-5.1 Codex mini (high)ClosedOpenAI | 20.4 | $0.69 | — | — |
| 44 | — | o3ClosedOpenAI | 20.2 | $3.5 | 140 | 6.1 s |
| 45 | — | Claude 4 Sonnet (Reasoning)ClosedAnthropic · 1 more variant | 18.9 | — | — | — |
| 46 | — | Claude 3.7 Sonnet (Reasoning)ClosedAnthropic · 1 more variant | 17.7 | — | — | — |
| 47 | — | Claude 4.5 Haiku (Reasoning)ClosedAnthropic · 1 more variant | 16.9 | $2.0 | 90 | 16 s |
| 48 | ▲ 1 | o4-mini (high)ClosedOpenAI | 16.7 | $1.9 | 158 | 27 s |
| 49 | ▼ 1 | Gemini 2.5 ProClosedGoogle | 16.1 | $3.4 | 141 | 24 s |
| 50 | — | Gemini 3.1 Flash-LiteClosedGoogle | 15.6 | $0.56 | 357 | 5.5 s |
Intelligence over time
Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi