Benchmark
DeepSearchQA
Scores are percentages. Higher is better.
- Models and systems measured
- 24
- Scores recorded
- 68
- Sources
- 3
- IQ weight
- 2.70
Score distribution
- 69.3%
- Mean
- 73.6%
- Median
- 18.7%
- Std dev
- 42%
- 10th percentile
- 91%
- 90th percentile
- 22%
- Min
This benchmark has a weight of 2.70 for chat models, measured over 23 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model or system | Score |
|---|---|---|
| 1 | Kimi K3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 95% |
| 2 | 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. | 95% |
| 3 | Claude Opus 4.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 93.1% |
| 4 | GPT-5.6 Solmax · 900 questions · common browser search/open/find harness · semantic answer matching· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 93.1% |
| 5 | Kimi K2.6Kimi K2.6 official benchmark table · thinking · temp 1.0 · top_p 1.0 · 262,144 context · no context management; over-length tasks counted failed· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 92.5% |
| 6 | Claude Opus 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 91.3% |
| 7 | Claude Sonnet 4.6multi-agent orchestrator · 3M tokens per agent · max effort· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 91.1% |
| 8 | Hy3 (Deep Infra)· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 91% |
| 9 | Hy3 (Deep Infra)Hy3 official Benchmark Appendix · highest reasoning tier unless noted· Reported by Tencent Hunyuan· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 91% |
| 10 | Claude Opus 5max · 900 questions · common browser search/open/find harness · semantic answer matching· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 90.4% |
| 11 | Muse Spark 1.3max · 900 questions · common browser search/open/find harness · semantic answer matching· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 90.3% |
| 12 | Muse Spark 1.3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 89.4% |
| 13 | Claude Sonnet 4.6single agent · 10M total tokens · search/fetch/code · adaptive thinking · max effort· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 89.2% |
| 14 | Claude Opus 4.7search/fetch + code · adaptive thinking · max effort · 10M total tokens · compaction at 200K· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 89.1% |
| 15 | GPT 5.5xhigh · browser search/open/find · gpt-oss-120b answer extraction· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 87.8% |
| 16 | MiMo V2 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 86.7% |
| 17 | MiMo V2 ProXiaomi MiMo-V2-Pro release table · search-agent setting · harness unspecified· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 86.7% |
| 18 | Muse Spark 1.2xhigh · 900 questions · common browser search/open/find harness · semantic answer matching· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 85.9% |
| 19 | Inkling 2 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 85.3% |
| 20 | Muse Spark 1.1Meta Model API · xhigh · browser search/open/find · gpt-oss-120b answer extraction· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 84.9% |
| 21 | Claude Opus 4.8max · browser search/open/find · gpt-oss-120b answer extraction· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 84.3% |
| 22 | Kimi K2.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 83% |
| 23 | Beam 1.0 501B A23B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 80.5% |
| 24 | Kimi K2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 77.1% |
| 25 | Kimi K2.5setting not named by the source· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 77.1% |
| 26 | Claude Opus 5OpenRouter harness, anthropic/claude-opus-5, parallel, server-tool, 25, high· OpenRouter benchmark exports | 77% |
| 27 | Claude Opus 5OpenRouter harness, anthropic/claude-opus-5, perplexity, server-tool, 25, high· OpenRouter benchmark exports | 76.5% |
| 28 | GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, native, server-tool, 25, high· OpenRouter benchmark exports | 75% |
| 29 | Muse Spark· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 74.8% |
| 30 | Muse Glimmer 30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 74.6% |
| 31 | Muse Glimmer 30Bhigh reasoning· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 74.6% |
| 32 | GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, parallel, server-tool, 25, high· OpenRouter benchmark exports | 73.6% |
| 33 | GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, perplexity, server-tool, 25, high· OpenRouter benchmark exports | 73.6% |
| 34 | GPT-5.6 LunaOpenRouter harness, openai/gpt-5.6-luna, perplexity, server-tool, 25, xhigh· OpenRouter benchmark exports | 73% |
| 35 | Mercury 3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 71.3% |
| 36 | Gemini 3.1 Pro Previewhigh · browser search/open/find · gpt-oss-120b answer extraction· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 71.3% |
| 37 | Claude Opus 5OpenRouter harness, anthropic/claude-opus-5, exa, server-tool, 25, high· OpenRouter benchmark exports | 70.5% |
| 38 | DeepSeek V4 Flash 0731OpenRouter harness, deepseek/deepseek-v4-flash-0731, perplexity, server-tool, 25, high· OpenRouter benchmark exports | 69% |
| 39 | GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, exa, server-tool, 25, high· OpenRouter benchmark exports | 69% |
| 40 | GPT-5.6 LunaOpenRouter harness, openai/gpt-5.6-luna, exa, server-tool, 25, xhigh· OpenRouter benchmark exports | 67% |
| 41 | GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, native, server-tool, 5, high· OpenRouter benchmark exports | 67% |
| 42 | Claude Opus 5OpenRouter harness, anthropic/claude-opus-5, perplexity, server-tool, 5, high· OpenRouter benchmark exports | 64.7% |
| 43 | DeepSeek V4 Flash 0731OpenRouter harness, deepseek/deepseek-v4-flash-0731, parallel, server-tool, 25, high· OpenRouter benchmark exports | 64% |
| 44 | GPT-5.6 LunaOpenRouter harness, openai/gpt-5.6-luna, parallel, server-tool, 25, xhigh· OpenRouter benchmark exports | 63% |
| 45 | DeepSeek V4 Flash 0731OpenRouter harness, deepseek/deepseek-v4-flash-0731, exa, server-tool, 25, high· OpenRouter benchmark exports | 60% |
| 46 | GPT-5.6 LunaOpenRouter harness, openai/gpt-5.6-luna, perplexity, server-tool, 5, xhigh· OpenRouter benchmark exports | 60% |
| 47 | GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, perplexity, server-tool, 5, high· OpenRouter benchmark exports | 59.8% |
| 48 | GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, parallel, server-tool, 5, high· OpenRouter benchmark exports | 59.4% |
| 49 | Claude Opus 5OpenRouter harness, anthropic/claude-opus-5, parallel, server-tool, 5, high· OpenRouter benchmark exports | 58% |
| 50 | GPT-5.6 SolOpenRouter harness, openai/gpt-5.6-sol, exa, server-tool, 5, high· OpenRouter benchmark exports | 57.9% |
Showing 1–50 of 67 results.
Not ranked
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model or system | Score |
|---|---|
| Muse Spark (version unspecified)Meta Model API · highest effort · version unspecified · browser search/open/find · gpt-oss-120b answer extraction· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 76.8% |
Data credits: Data by LLM Stats · 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. · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence)