models.fyi

Every score below is at the effort you pick — not the press-release number.

Public leaderboards quote each model at maximum reasoning effort. Nobody runs xhigh for everything. Choose a tier and see what the models are actually worth there — models that don't support the tier resolve to their nearest one (shown per row).

ProprietaryOpen weights
↑ better · ← cheaper

Cost per typical task, log scale (1K in + 600 out + reasoning tokens)

#ModelEffort usedIndexGPQAAIMESWE-benchCost / task$/M in · outtok/sCtx
1Claude Fable 5
Anthropic
Low70.773.867.270.5$0.080$10 · $50651M
2GPT-5.5
OpenAI
Low69.473.067.967.1$0.012$1.25 · $10140400K
3Claude Opus 4.8
Anthropic
Low68.672.265.168.8$0.037$5 · $25551M
4Gemini 3 Pro
Google
Low63.768.356.361.6$0.016$2 · $121301M
5Claude Sonnet 5
Anthropic
Low62.465.654.962.7$0.019$3 · $15801M
6Grok 4.1
xAI
Low61.665.354.559.2$0.022$3 · $1590256K
7GLM-5.2
Zhipu AI
Low61.363.853.461.6$0.0032$0.60 · $2.2095200K
8DeepSeek-V3.2
DeepSeek
Low60.964.856.159.4$0.0007$0.28 · $0.4260128K
9Qwen3-235B-A22B
Alibaba
Low58.563.353.656.1$0.0038$0.70 · $2.8070128K
10Kimi K2 Thinking
Moonshot AI
Low54.157.242.652.4$0.0043$0.60 · $2.5050256K
11Llama 4 Maverick
Meta
Standard52.470.040.044.0$0.0008$0.27 · $0.851601M

Index = weighted composite of 8 benchmarks (weights on /benchmarks) · cost/task assumes 1K in + 600 out + the tier's typical reasoning tokens · preview data.