RankingHLE (wo / w tools) · source release snapshot; version not specified
HLE (wo / w tools) · source release snapshot; version not specified
- Bucket
- Hard reasoning
- Unit
- percent
- Direction
- Higher is better
- Version
- source release snapshot; version not specified
- Display harness
- deepseek-ai/DeepSeek-V4-Pro-0813
- Board
- https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813
Compare published benchmark results with category weights →
Models
| Model | Score | Harness | Evidence | Source-recorded date |
|---|---|---|---|---|
| Claude Fable 5Anthropic | 53.3%Reported settings & sourceDeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card. without tools First-party reported result. Comparison limit: The source labels this column Fable-5 (w/ fallback); it does not establish standalone Fable 5 performance. Retained as published evidence, excluded from comparable ranking inputs. deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: HLE (wo / w tools) · reviewed 2026-09-12 | deepseek-ai/DeepSeek-V4-Pro-0813 | lab self-report | 2026-09-12 |
| Claude Opus 4.8Anthropic | 49.8%Reported settings & sourceDeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card. without tools First-party reported result. deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: HLE (wo / w tools) · reviewed 2026-09-12 | deepseek-ai/DeepSeek-V4-Pro-0813 | lab self-report | 2026-09-12 |
| Kimi K3Moonshot | 43.5%Reported settings & sourceDeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card. without tools First-party reported result. deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: HLE (wo / w tools) · reviewed 2026-09-12 | deepseek-ai/DeepSeek-V4-Pro-0813 | lab self-report | 2026-09-12 |
| DeepSeek V4-Pro 0813DeepSeek | 42.7%Reported settings & sourceDeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card. without tools First-party reported result. deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: HLE (wo / w tools) · reviewed 2026-09-12 | deepseek-ai/DeepSeek-V4-Pro-0813 | lab self-report | 2026-09-12 |
| GLM-5.2Z.ai | 40.5%Reported settings & sourceDeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card. without tools First-party reported result. deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: HLE (wo / w tools) · reviewed 2026-09-12 | deepseek-ai/DeepSeek-V4-Pro-0813 | lab self-report | 2026-09-12 |
| DeepSeek-V4-Flash-0731DeepSeek | 37.8%Reported settings & sourceDeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card. without tools First-party reported result. deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: HLE (wo / w tools) · reviewed 2026-09-12 | deepseek-ai/DeepSeek-V4-Pro-0813 | lab self-report | 2026-09-12 |
| Claude Fable 5Anthropic | 63%Reported settings & sourceDeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card. with tools First-party reported result. Comparison limit: The source labels this column Fable-5 (w/ fallback); it does not establish standalone Fable 5 performance. Retained as published evidence, excluded from comparable ranking inputs. deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: HLE (wo / w tools) · reviewed 2026-09-12 | deepseek-ai/DeepSeek-V4-Pro-0813 | lab self-report | 2026-09-12 |
| Claude Opus 4.8Anthropic | 57.9%Reported settings & sourceDeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card. with tools First-party reported result. deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: HLE (wo / w tools) · reviewed 2026-09-12 | deepseek-ai/DeepSeek-V4-Pro-0813 | lab self-report | 2026-09-12 |
| DeepSeek V4-Pro 0813DeepSeek | 60%Reported settings & sourceDeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card. with tools First-party reported result. deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: HLE (wo / w tools) · reviewed 2026-09-12 | deepseek-ai/DeepSeek-V4-Pro-0813 | lab self-report | 2026-09-12 |
| DeepSeek-V4-Flash-0731DeepSeek | 51.5%Reported settings & sourceDeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card. with tools First-party reported result. deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: HLE (wo / w tools) · reviewed 2026-09-12 | deepseek-ai/DeepSeek-V4-Pro-0813 | lab self-report | 2026-09-12 |
| GLM-5.2Z.ai | 54.7%Reported settings & sourceDeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card. with tools First-party reported result. deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: HLE (wo / w tools) · reviewed 2026-09-12 | deepseek-ai/DeepSeek-V4-Pro-0813 | lab self-report | 2026-09-12 |
| Kimi K3Moonshot | 56%Reported settings & sourceDeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card. with tools First-party reported result. deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: HLE (wo / w tools) · reviewed 2026-09-12 | deepseek-ai/DeepSeek-V4-Pro-0813 | lab self-report | 2026-09-12 |