01·Leaderboard
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 · ← cheaperCost per typical task, log scale (1K in + 600 out + reasoning tokens)
| # | Model | Effort used | Index | GPQA | AIME | SWE-bench | Cost / task | $/M in · out | tok/s | Ctx |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5 Anthropic | Medium | 78.0 | 82.8 | 82.6 | 77.1 | $0.19 | $10 · $50 | 65 | 1M |
| 2 | GPT-5.5 OpenAI | Medium | 76.6 | 81.9 | 83.4 | 73.3 | $0.032 | $1.25 · $10 | 140 | 400K |
| 3 | Claude Opus 4.8 Anthropic | Medium | 75.5 | 81.0 | 80.0 | 75.2 | $0.090 | $5 · $25 | 55 | 1M |
| 4 | Gemini 3 Pro Google | Medium | 72.7 | 80.1 | 75.7 | 69.3 | $0.040 | $2 · $12 | 130 | 1M |
| 5 | Claude Sonnet 5 Anthropic | Medium | 71.1 | 77.0 | 73.8 | 70.5 | $0.042 | $3 · $15 | 80 | 1M |
| 6 | Grok 4.1 xAI | Medium | 70.2 | 76.6 | 73.3 | 66.6 | $0.057 | $3 · $15 | 90 | 256K |
| 7 | GLM-5.2 Zhipu AI | Medium | 69.9 | 74.8 | 71.8 | 69.3 | $0.0072 | $0.60 · $2.20 | 95 | 200K |
| 8 | DeepSeek-V3.2 DeepSeek | Medium | 69.5 | 76.1 | 75.5 | 66.8 | $0.0015 | $0.28 · $0.42 | 60 | 128K |
| 9 | Qwen3-235B-A22B Alibaba | Medium | 66.7 | 74.3 | 72.1 | 63.1 | $0.0080 | $0.70 · $2.80 | 70 | 128K |
| 10 | Kimi K2 Thinking Moonshot AI | Medium | 65.7 | 72.7 | 66.3 | 62.6 | $0.011 | $0.60 · $2.50 | 50 | 256K |
| 11 | Llama 4 Maverick Meta | Standard | 52.4 | 70.0 | 40.0 | 44.0 | $0.0008 | $0.27 · $0.85 | 160 | 1M |
Index = weighted composite of 8 benchmarks (weights on /benchmarks) · cost/task assumes 1K in + 600 out + the tier's typical reasoning tokens · preview data.