Benchmark
DeepResearch Bench II
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.
- Models measured
- 6
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- 0.44
Score distribution
- 50.8%
- Mean
- 51.3%
- Median
- 2.4%
- Std dev
- 49.2%
- 10th percentile
- 54.1%
- 90th percentile
- 46.6%
- Min
This benchmark has a weight of 0.44 for chat models, measured over 6 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 5Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · Claude Code · identical search tools · four-hour task limit · GPT-5.5 judge · three independent scoring passes· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 54.1% |
| 2 | GLM 5.3Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · Claude Code · identical search tools · four-hour task limit · GPT-5.5 judge · three independent scoring passes· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 52.7% |
| 3 | Kimi K3Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · Claude Code · identical search tools · four-hour task limit · GPT-5.5 judge · three independent scoring passes· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 51.3% |
| 4 | GPT-5.6 SolAtria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · Claude Code · identical search tools · four-hour task limit · GPT-5.5 judge · three independent scoring passes· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 50.7% |
| 5 | Qwen3.8 MaxAtria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · Claude Code · identical search tools · four-hour task limit · GPT-5.5 judge · three independent scoring passes· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 49.2% |
| 6 | DeepSeek V4 Pro 0813Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · Claude Code · identical search tools · four-hour task limit · GPT-5.5 judge · three independent scoring passes· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 46.6% |