← Global
math
math ranking
index v0.1.0 · run cmsfulul · 2026-08-05 08:51 UTC| # | Model | Provider | Score (95% CI) | Consist. | Calib. | Contam. Δ | p50 | $/1k | |
|---|---|---|---|---|---|---|---|---|---|
| 1 | deepseek | 825 [681–969] | 0.92 | 1.00 | 0.000 | 525ms | $0.029 | ||
| 2 | amazon | 783 [644–922] | 0.93 | 0.97 | 0.000 | 325ms | $2.86 | ||
| 3 | anthropic | 659 [545–772] | 0.95 | 0.83 | 0.000 | 3.4s | $8.18 | ||
| 4 | anthropic | 627 [522–732] | 0.95 | 0.78 | 0.000 | 3.0s | $0.912 | ||
| 5 | anthropic | 541 [451–631] | 1.00 | 0.71 | 0.058 | 1.1s | $1.65 |
- 825 [681–969]consist 0.92calib 1.00Δ 0.000525ms$0.029/1k
- 783 [644–922]consist 0.93calib 0.97Δ 0.000325ms$2.86/1k
- #3Anthropic: Claude Fable 5anthropic659 [545–772]consist 0.95calib 0.83Δ 0.0003.4s$8.18/1k
- #4Anthropic: Claude Sonnet 5anthropic627 [522–732]consist 0.95calib 0.78Δ 0.0003.0s$0.912/1k
- #5Anthropic: Claude Sonnet 4.6anthropic541 [451–631]consist 1.00calib 0.71Δ 0.0581.1s$1.65/1k