Model rankings
481 models · 3 boards · 2 sources
Smartest
Best open model
Best value
Best from China
Top three open models
Qwen3 235B A22B 2507 (Reasoning)Alibaba · #6 overall68.9
DeepSeek R1 0528 (May '25)DeepSeek · #8 overall68.3
GLM-4.5Z AI · #10 overall65.7
This week's changes
GLM-4.5Intelligence · #10New
EXAONE 4.0 32B (Reasoning)Intelligence · #14New
Llama Nemotron Super 49B v1.5 (Reasoning)Intelligence · #16New
Sonar Reasoning ProIntelligence · #21New
GLM-4.5-AirIntelligence · #24New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | Grok 4ClosedxAI | 73.2 | $6.0 | — | — |
| 2 | — | o3-proClosedOpenAI | 71.0 | $35 | — | — |
| 3 | — | Gemini 2.5 ProClosedGoogle | 70.5 | $3.4 | — | — |
| 4 | — | o3ClosedOpenAI | 70.0 | $3.5 | — | — |
| 5 | — | o4-mini (high)ClosedOpenAI | 69.8 | $1.9 | — | — |
| 6 | — | Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle · 1 more variant | 68.9 | $3.4 | — | — |
| 7 | — | Grok 3 mini Reasoning (high)ClosedxAI | 66.7 | $0.35 | — | — |
| 8 | — | o3-mini (high)ClosedOpenAI · 1 more variant | 65.5 | $1.9 | — | — |
| 9 | — | Gemini 2.5 Flash (Reasoning)ClosedGoogle · 1 more variant | 65.1 | $0.85 | — | — |
| 10 | — | Claude 4 Opus (Extended Thinking)ClosedAnthropic · 1 more variant | 64.4 | $30 | — | — |
| 11 | — | Claude 4 Sonnet (Extended Thinking)ClosedAnthropic · 1 more variant | 63.8 | $6.0 | — | — |
| 12 | — | o1ClosedOpenAI · 1 more variant | 61.9 | $26 | — | — |
| 13 | New | Sonar Reasoning ProClosedPerplexity | 61.0 | $0.000 | — | — |
| 14 | ▼ 1 | Gemini 2.5 Flash Preview (Reasoning)ClosedGoogle · 1 more variant | 60.5 | $0.99 | — | — |
| 15 | ▼ 1 | Solar Pro 2 (Reasoning)ClosedUpstage · 3 more variants | 58.2 | $0.50 | — | — |
| 16 | ▼ 1 | Claude 3.7 Sonnet (Extended Thinking)ClosedAnthropic · 1 more variant | 57.4 | $6.0 | — | — |
| 17 | ▼ 1 | Grok 3 Reasoning BetaClosedxAI | 56.1 | $0.000 | — | — |
| 17 | ▼ 1 | o1-proClosedOpenAI | 56.1 | $263 | — | — |
| 19 | ▼ 1 | Magistral MediumClosedMistral | 56.0 | $2.8 | — | — |
| 20 | ▼ 1 | Gemini 2.5 Flash-Lite (Reasoning)ClosedGoogle · 1 more variant | 54.9 | $0.18 | — | — |
| 21 | ▼ 1 | o1-miniClosedOpenAI | 53.8 | $1.9 | — | — |
| 22 | ▲ 7 | Sonar ReasoningClosedPerplexity | 53.4 | $2.0 | — | — |
| 23 | ▼ 2 | GPT-4.5 (Preview)ClosedOpenAI | 53.0 | $0.000 | — | — |
| 24 | ▼ 2 | GPT-4.1 miniClosedOpenAI | 52.9 | $0.70 | — | — |
| 25 | ▼ 2 | GPT-4.1ClosedOpenAI | 52.6 | $3.5 | — | — |
| 26 | ▼ 2 | Gemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle | 52.3 | $0.000 | — | — |
| 27 | ▼ 2 | Grok 3ClosedxAI | 50.6 | $6.0 | — | — |
| 28 | ▼ 2 | GPT-4o (March 2025, chatgpt-4o-latest)ClosedOpenAI · 4 more variants | 50.3 | $7.5 | — | — |
| 29 | ▼ 2 | Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle | 49.2 | $0.000 | — | — |
| 30 | ▼ 2 | Mistral Medium 3ClosedMistral | 49.0 | $0.80 | — | — |
| 31 | ▼ 1 | Gemini 2.0 Flash (Feb '25)ClosedGoogle · 1 more variant | 48.4 | $0.18 | — | — |
| 32 | ▼ 1 | Qwen2.5 MaxClosedAlibaba | 45.3 | $2.8 | — | — |
| 33 | ▼ 1 | Gemini 1.5 Pro (Sep '24)ClosedGoogle · 1 more variant | 44.6 | $0.000 | — | — |
| 34 | ▼ 1 | Claude 3.5 Sonnet (Oct '24)ClosedAnthropic · 1 more variant | 44.4 | $6.0 | — | — |
| 35 | ▼ 1 | SonarClosedPerplexity | 43.4 | $1.0 | — | — |
| 36 | ▼ 1 | Sonar ProClosedPerplexity | 42.7 | $6.0 | — | — |
| 37 | ▼ 1 | Nova PremierClosedAmazon | 42.6 | $5.0 | — | — |
| 38 | ▼ 1 | Gemini 2.0 Flash-Lite (Feb '25)ClosedGoogle · 1 more variant | 41.4 | $0.13 | — | — |
| 39 | ▼ 1 | GPT-4.1 nanoClosedOpenAI | 41.0 | $0.18 | — | — |
| 40 | ▼ 1 | Grok 2 (Dec '24)ClosedxAI | 39.2 | $0.000 | — | — |
| 41 | ▼ 1 | Gemini 1.5 Flash (Sep '24)ClosedGoogle · 1 more variant | 39.0 | $0.000 | — | — |
| 42 | ▼ 1 | GPT-4 TurboClosedOpenAI | 38.8 | $15 | — | — |
| 43 | ▼ 1 | Devstral MediumClosedMistral | 38.2 | $0.80 | — | — |
| 44 | ▼ 1 | Grok BetaClosedxAI | 37.5 | $0.000 | — | — |
| 45 | ▼ 1 | Nova ProClosedAmazon | 37.1 | $1.4 | — | — |
| 46 | ▼ 1 | GPT-4ClosedOpenAI | 36.0 | $38 | — | — |
| 47 | ▼ 1 | GPT-4o miniClosedOpenAI | 35.7 | $0.26 | — | — |
| 48 | ▼ 1 | Claude 3 OpusClosedAnthropic | 35.1 | $30 | — | — |
| 49 | ▼ 1 | Claude 3.5 HaikuClosedAnthropic | 34.7 | $1.6 | — | — |
| 50 | ▼ 1 | Mistral SabaClosedMistral | 33.9 | $0.30 | — | — |
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