Benchmark
SurveyReview v1.0 · Overall · Reason Quality Score
Higher scores are better.
Benchmark sourceScores from BenchBoard docs.
- Models and systems measured
- 7
- Scores recorded
- 7
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 0.379
- Mean
- 0.37
- Median
- 0.054
- Std dev
- 0.36
- 10th percentile
- 0.42
- 90th percentile
- 0.29
- Min
Leaderboard
| # | Model or system | Score |
|---|---|---|
| 1 | Claude Opus 4.5SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table· Reported by SurveyReview authors / Z.ai· via BenchBoard docs | 0.48 |
| 2 | GPT 5.2SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table· Reported by SurveyReview authors / Z.ai· via BenchBoard docs | 0.42 |
| 3 | DeepSeek V3.2SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table· Reported by SurveyReview authors / Z.ai· via BenchBoard docs | 0.37 |
| 4 | Gemini 3 Pro PreviewSurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table· Reported by SurveyReview authors / Z.ai· via BenchBoard docs | 0.29 |
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 |
|---|---|
| GLM-4.7 (SurveyReview v1.0 label)SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table· Reported by SurveyReview authors / Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 0.37 |
| Qwen3-32B (SurveyReview v1.0 label)SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table· Reported by SurveyReview authors / Z.ai· via BenchBoard docs | 0.36 |
| SurveyReviewer (SurveyReview v1.0 label)SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table· Reported by SurveyReview authors / Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 0.36 |