Model rankings
1055 models · 5 boards · 2 sources
Best web builder
Best open model
Best from China
Most voted
Top three by Score
claude-opus-4-6-thinkingAnthropic1,552
claude-sonnet-4-6Anthropic1,524
claude-opus-4-5-20251101-thinking-32kAnthropic1,493
Top three open models
glm-5Z.ai · #7 overall1,447
glm-4.7Z.ai · #8 overall1,442
kimi-k2.5-thinkingMoonshot AI · #11 overall1,437
This week's changes
GPT-5.4 (xhigh)Intelligence · #2New
gpt-5.4-high (codex-harness)Coding · #5New
gpt-5.4-medium (codex-harness)Coding · #12New
Step 3.5 FlashIntelligence · #35New
Gemini 3.1 Flash-Lite PreviewIntelligence · #46New
| Rank | Change | Model | Score | 95% interval | Votes | Price $/M |
|---|---|---|---|---|---|---|
| 1 | — | claude-opus-4-6-thinkingClosedAnthropic · 1 more variant | 1,552 | ±13 | 2,891 | — |
| 2 | — | claude-sonnet-4-6ClosedAnthropic | 1,524 | ±11 | 4,322 | — |
| 3 | — | claude-opus-4-5-20251101-thinking-32kClosedAnthropic | 1,493 | ±7 | 12,499 | — |
| 4 | — | claude-opus-4-5-20251101ClosedAnthropic | 1,472 | ±7 | 12,651 | — |
| 5 | New | gpt-5.4-high (codex-harness)ClosedOpenAI | 1,460 | ±17 | 1,410 | — |
| 6 | ▼ 1 | gemini-3.1-pro-previewClosedGoogle | 1,457 | ±11 | 3,510 | — |
| 7 | — | gemini-3-flashClosedGoogle · 1 more variant | 1,441 | ±7 | 13,639 | — |
| 8 | ▼ 2 | gemini-3-proClosedGoogle | 1,440 | ±7 | 17,867 | — |
| 9 | New | gpt-5.4-medium (codex-harness)ClosedOpenAI | 1,436 | ±18 | 1,271 | — |
| 10 | ▼ 2 | gpt-5.3-codex (codex-harness)ClosedOpenAI | 1,406 | ±12 | 2,817 | — |
| 11 | ▼ 2 | gpt-5.2ClosedOpenAI | 1,395 | ±15 | 1,644 | — |
| 12 | ▼ 2 | gpt-5-mediumClosedOpenAI | 1,393 | ±12 | 3,948 | — |
| 13 | ▼ 2 | claude-sonnet-4-5-20250929-thinking-32kClosedAnthropic | 1,391 | ±7 | 15,434 | — |
| 14 | ▼ 1 | gpt-5.1-mediumClosedOpenAI | 1,389 | ±9 | 6,468 | — |
| 15 | ▼ 3 | claude-opus-4-1-20250805ClosedAnthropic | 1,388 | ±9 | 9,020 | — |
| 16 | ▼ 2 | claude-sonnet-4-5-20250929ClosedAnthropic | 1,386 | ±7 | 17,248 | — |
| 17 | ▼ 2 | gpt-5.1ClosedOpenAI | 1,343 | ±7 | 13,323 | — |
| 18 | ▼ 2 | gpt-5.2-codexClosedOpenAI | 1,342 | ±8 | 7,022 | — |
| 19 | ▼ 2 | gpt-5.1-codexClosedOpenAI | 1,329 | ±9 | 6,553 | — |
| 20 | ▼ 2 | claude-haiku-4-5-20251001ClosedAnthropic | 1,309 | ±7 | 15,200 | $2.0 |
| 21 | ▼ 2 | KAT-Coder-Pro-V1ClosedKwaiKAT | 1,260 | ±15 | 1,964 | — |
| 22 | ▼ 2 | gemini-3.1-flash-lite-previewClosedGoogle | 1,254 | ±17 | 1,397 | $0.56 |
| 23 | ▼ 2 | gpt-5.1-codex-miniClosedOpenAI | 1,244 | ±17 | 1,541 | — |
| 24 | ▼ 2 | qwen3.5-flashClosedAlibaba | 1,243 | ±17 | 1,538 | — |
| 25 | ▼ 2 | grok-4-1-fast-reasoningClosedxAI | 1,236 | ±9 | 7,144 | — |
| 26 | ▼ 2 | gemini-2.5-proClosedGoogle | 1,206 | ±13 | 3,477 | — |
| 27 | ▼ 2 | grok-4.1-thinkingClosedxAI | 1,205 | ±19 | 1,282 | — |
| 28 | ▼ 2 | grok-4-fast-reasoningClosedxAI | 1,151 | ±23 | 968 | — |
| 29 | ▼ 2 | grok-code-fast-1ClosedxAI | 1,143 | ±21 | 1,021 | — |
| 30 | ▼ 2 | devstral-medium-2507ClosedMistral | 1,100 | ±22 | 1,027 | — |
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