Model directory
Compare AI models
Compare AI models by intelligence, speed, latency, pricing, context window, and more. Values come from catalog summary cards; certified leaderboard ranks publish separately when evidence exists.
- Catalog profiles
- 550
- Providers
- 52
- Models ranked
- 0
Source: Canonical model registry at build time · 550 catalog rows
Catalog profiles
550 / 550
- AnthropicClaude Fable 5 (with fallback)
- Intelligence
- 60
- Speed
- 70.7
- Context
- 1M
- Output
- $50.00
- AnthropicClaude Opus 4.8 (max)
- Intelligence
- 56
- Speed
- 64.5
- Context
- 1M
- Output
- $25.00
- OpenAIGPT-5.5 (xhigh)
- Intelligence
- 55
- Speed
- 88.0
- Context
- 920k
- Output
- $30.00
- AnthropicClaude Opus 4.7 (max)
- Intelligence
- 54
- Speed
- 56.4
- Context
- 1M
- Output
- $25.00
- AnthropicClaude Sonnet 5 (max)
- Intelligence
- 53
- Speed
- 83.7
- Context
- 1M
- Output
- $10.00
- OpenAIGPT-5.5 (high)
- Intelligence
- 53
- Speed
- 83.1
- Context
- 920k
- Output
- $30.00
- Z AIGLM-5.2 (max)
- Intelligence
- 51
- Speed
- 217.6
- Context
- 1M
- Output
- $4.40
- OpenAIGPT-5.4 (xhigh)
- Intelligence
- 51
- Speed
- 175.3
- Context
- 1.1M
- Output
- $15.00
- GoogleGemini 3.5 Flash
- Intelligence
- 50
- Speed
- 192.2
- Context
- 1M
- Output
- $9.00
- OpenAIGPT-5.5 (medium)
- Intelligence
- 50
- Speed
- 72.7
- Context
- 920k
- Output
- $30.00
- AnthropicClaude Sonnet 4.6 (max)
- Intelligence
- 47
- Speed
- 71.0
- Context
- 1M
- Output
- $15.00
- GoogleGemini 3.1 Pro Preview
- Intelligence
- 46
- Speed
- 151.6
- Context
- 1M
- Output
- $12.00
- AlibabaQwen3.7 Max
- Intelligence
- 46
- Speed
- 206.4
- Context
- 3.7M
- Output
- $7.50
- GoogleGemini 3.5 Flash (medium)
- Intelligence
- 45
- Speed
- 191.4
- Context
- 1M
- Output
- $9.00
- AnthropicClaude Opus 4.6 (max)
- Intelligence
- 44
- Speed
- 43.7
- Context
- 1M
- Output
- $25.00
- DeepSeekDeepSeek V4 Pro (max)
- Intelligence
- 44
- Speed
- 72.0
- Context
- 1M
- Output
- $0.87
- OpenAIGPT-5.3 Codex (xhigh)
- Intelligence
- 44
- Speed
- 99.0
- Context
- 400k
- Output
- $14.00
- KimiKimi K2.6
- Intelligence
- 44
- Speed
- 76.2
- Context
- 260k
- Output
- $4.00
- MiniMaxMiniMax-M3
- Intelligence
- 44
- Speed
- 99.0
- Context
- 1M
- Output
- $1.20
- AnthropicClaude Opus 4.7 (Non-reasoning, high)
- Intelligence
- 43
- Speed
- 50.5
- Context
- 1M
- Output
- $25.00
- OpenAIGPT-5.5 (low)
- Intelligence
- 43
- Speed
- 81.7
- Context
- 920k
- Output
- $30.00
- MetaMuse Spark
- Intelligence
- 43
- Speed
- —
- Context
- 260k
- Output
- —
- AnthropicClaude Sonnet 5 (Non-reasoning)
- Intelligence
- 42
- Speed
- —
- Context
- 1M
- Output
- $10.00
- OpenAIGPT-5.2 (xhigh)
- Intelligence
- 42
- Speed
- 84.4
- Context
- 400k
- Output
- $14.00
1 / 23
Leaderboards
Rankings are currently unavailable. Canonical results have not been certified.
No certified ranking evidence is published yet.
- Intelligence
- Higher · score
- Speed
- Higher · tok/s
- Latency
- Lower · s TTFT
- Input Price
- Lower · $/1M tokens
- Output Price
- Lower · $/1M tokens
- Context Window
- Higher · tokens
- 01All modelsBrowse catalog profiles with available summary metrics.
- 02ProvidersProvider roster derived from the canonical index.
- 03LeaderboardsMetric views. Rankings appear only when certified results exist.
- 04BenchmarksEvaluation dimensions with method, unit, and direction.