| 1 |  Anthropic | claude-opus-5.5-max95% 区间:1,798 – 1,828名次区间:1 ↔ 1 1,813+15/-15 | 2,294 | $4 / $20 | 1M | | › |
| 2 | | gpt-6-astra-max95% 区间:1,775 – 1,797名次区间:2 ↔ 3 1,786+11/-11 | 5,189 | $10 / $50 | 1.1M | | › |
| 3 |  Anthropic | claude-sonnet-5.5-xhigh95% 区间:1,759 – 1,789名次区间:2 ↔ 4 1,774+15/-15 | 2,323 | $2 / $10 | 1M | | › |
| 4 | | gpt-6.1-sol-max95% 区间:1,740 – 1,770名次区间:3 ↔ 5 1,755+15/-15 | 2,102 | $2 / $10 | 1.1M | | › |
| 5 |  Anthropic | claude-fable-5.1-max95% 区间:1,734 – 1,753名次区间:4 ↔ 5 1,744+9/-9 | 6,663 | $10 / $50 | 1M | | › |
| 6 |  Anthropic | claude-sonnet-5.5-high95% 区间:1,704 – 1,726名次区间:6 ↔ 6 1,715+11/-11 | 3,984 | $2 / $10 | 1M | | › |
| 7 |  Anthropic | claude-opus-5-max95% 区间:1,685 – 1,698名次区间:7 ↔ 9 1,691+6/-6 | 17,320 | $5 / $25 | 1M | | › |
| 8 | | gpt-6-sol-max95% 区间:1,676 – 1,700名次区间:7 ↔ 11 1,688+12/-12 | 3,407 | $2 / $10 | 1.1M | | › |
| 9 |  Google | gemini-4-argon-high95% 区间:1,662 – 1,693名次区间:7 ↔ 13 1,678+15/-15 | 1,771 | — | — | | › |
| 10 |  Alibaba↑1 | qwen3.8-max-090295% 区间:1,666 – 1,681名次区间:8 ↔ 11 1,674+8/-8 | 11,182 | — | — | | › |
| 11 | | qwen3.8-max95% 区间:1,660 – 1,684名次区间:8 ↔ 14 1,672+12/-12 | 3,446 | $2 / $6 | 1M | | › |
| 12 |  Anthropic | claude-opus-5-high95% 区间:1,651 – 1,662名次区间:10 ↔ 14 1,657+6/-6 | 22,340 | $5 / $25 | 1M | | › |
| 13 | | muse-spark-1.3-max95% 区间:1,649 – 1,665名次区间:10 ↔ 15 1,657+8/-8 | 7,886 | $1.25 / $4.25 | 1M | | › |
| 14 | | kimi-k3-max95% 区间:1,648 – 1,661名次区间:11 ↔ 15 1,654+6/-6 | 17,412 | $3 / $15 | 1M | | › |
| 15 | | grok-4.7-xhigh95% 区间:1,628 – 1,650名次区间:13 ↔ 23 1,639+11/-11 | 3,936 | $2 / $6 | 500K | | › |
| 16 | | mimo-v2.6-flash95% 区间:1,626 – 1,647名次区间:15 ↔ 23 1,637+10/-10 | 4,058 | $0.14 / $0.28 | 1M | | › |
| 17 |  Alibaba开源 | qwen3.8-flash-next95% 区间:1,624 – 1,641名次区间:15 ↔ 25 1,633+8/-8 | 6,932 | — | — | | › |
| 18 | | hy4-preview95% 区间:1,622 – 1,641名次区间:15 ↔ 25 1,632+10/-10 | 4,792 | $0.83 / $2.50 | 1M | | › |
| 19 | | mimo-v2.6-pro95% 区间:1,618 – 1,640名次区间:15 ↔ 25 1,629+11/-11 | 3,649 | $0.43 / $0.87 | 1M | | › |
| 20 |  Meta | muse-spark-1.3 (xHigh)95% 区间:1,617 – 1,634名次区间:15 ↔ 25 1,626+8/-8 | 7,123 | $1.25 / $4.25 | 1M | | › |
| 21 |  Anthropic | claude-fable-5-high95% 区间:1,618 – 1,631名次区间:15 ↔ 25 1,625+6/-6 | 14,657 | $10 / $50 | 1M | | › |
| 22 | | glm-5.3-max95% 区间:1,614 – 1,630名次区间:15 ↔ 26 1,622+8/-8 | 8,382 | $1.40 / $4.40 | 1M | | › |
| 23 |  DeepSeek开源 | deepseek-v4.1-flash-max95% 区间:1,608 – 1,630名次区间:15 ↔ 27 1,619+11/-11 | 3,542 | $0.15 / $0.60 | 1M | | › |
| 24 |  OpenAI | gpt-5.6-sol-xhigh (codex-harness)95% 区间:1,612 – 1,624名次区间:17 ↔ 26 1,618+6/-6 | 16,639 | — | — | | › |
| 25 | | grok-4.6-high95% 区间:1,609 – 1,625名次区间:17 ↔ 26 1,617+8/-8 | 8,958 | $2 / $6 | 500K | | › |