Benchmark
OfficeQA Pro
Scores are percentages. Higher is better.
- Models measured
- 22
- Scores recorded
- 34
- Sources
- 2
- IQ weight
- 1.14
Score distribution
- 60.7%
- Mean
- 63.3%
- Median
- 11%
- Std dev
- 47.1%
- 10th percentile
- 71.1%
- 90th percentile
- 18.1%
- Min
This benchmark has a weight of 1.14 for chat models, measured over 22 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7exact-match grading · 0% allowable relative error · system-card table· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 80.6% |
| 2 | Claude Fable 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 72.9% |
| 3 | Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 72.2% |
| 4 | Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 71.1% |
| 5 | Claude Fable 5.1Opus 5.5 System Card capability section · same Opus 5.5 card setup· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 69% |
| 6 | ERNIE 5.5 Flash Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 67.9% |
| 7 | Claude Opus 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 67.7% |
| 8 | Claude Opus 5.5Opus 5.5 System Card capability section · 133-question subset · extracted-text sandbox + code · max · 5 runs· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 67.7% |
| 9 | Kimi K3.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 67.4% |
| 10 | Claude Opus 5Opus 5.5 System Card capability section · same Opus 5.5 card setup· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 66.9% |
| 11 | Claude Opus 4.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 66.2% |
| 12 | Hy4 preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 66.2% |
| 13 | Hy4 previewofficial model-card appendix· Reported by Tencent Hy· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 66.2% |
| 14 | Claude Sonnet 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 65.6% |
| 15 | Claude Sonnet 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · 133-question subset · preselected extracted text + code · max · 5 runs· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 65.6% |
| 16 | Claude Opus 4.7launch-page office-tasks chart · published value conflicts with 80.6 in system card· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 65% |
| 17 | Kimi K3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 63.3% |
| 18 | Kimi K3max effort · temp 1.0 · top_p 1.0· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 63.3% |
| 19 | GLM 5.3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 62.4% |
| 20 | GLM 5.3 FlashTreasury Bulletin / 无嵌入文本· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 62.4% |
| 21 | Claude Haiku 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 60.3% |
| 22 | Claude Haiku 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · 133-question subset · preselected extracted text + code · max · 5 runs· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 60.3% |
| 23 | Claude Sonnet 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 59.4% |
| 24 | Claude Sonnet 5133-question subset · extracted-text sandbox + code · max effort · 5 trials· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 59.4% |
| 25 | Claude Fable 5Fable/Mythos 5 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 57.9% |
| 26 | GPT 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 54.1% |
| 27 | GPT 5.5xhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 54.1% |
| 28 | Claude Sonnet 4.6extracted-text sandbox + code · max effort · Sonnet 5 card rerun· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 53.4% |
| 29 | GPT 5.5Fable/Mythos 5 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 52.6% |
| 30 | Claude Opus 4.8Fable/Mythos 5 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 48.1% |
| 31 | Claude Haiku 4.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · 133-question subset · preselected extracted text + code · fixed thinking budget · 5 runs· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 47.1% |
| 32 | MiniMax M3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 45.1% |
| 33 | MiniMax M3Claude Code · filesystem delivery · exact match· Reported by MiniMax Research· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 45.1% |
| 34 | Gemini 3.1 Pro PreviewFable/Mythos 5 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 18.1% |
Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats