Benchmark
BabyVision
Scores are percentages. Higher is better.
- Models and systems measured
- 25
- Scores recorded
- 33
- Sources
- 2
- IQ weight
- 2.15
Score distribution
- 74.6%
- Mean
- 82%
- Median
- 18.5%
- Std dev
- 40.2%
- 10th percentile
- 92.5%
- 90th percentile
- 38.4%
- Min
This benchmark has a weight of 2.15 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 K3.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 95.4% |
| 2 | Claude Opus 5DeepSeek V4.1 launch chart · exact public value · setting not further specified · with tools· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 94.1% |
| 3 | DeepSeek V4.1 Flash 1017· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 92.5% |
| 4 | DeepSeek V4.1 Flash 1017DeepSeek 1017 first-party evaluation · reasoning effort, candidate sampling, exact run count, and unspecified harnesses not published · with tools · harness unspecified· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 92.5% |
| 5 | MiniMax M3.1 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 91% |
| 6 | MiniMax M3.1 FlashMiniMax M3.1 Flash official-weights model-card run · reasoning effort, sampling, and run count not stated for this benchmark · with tools · Claude Code 2.1.285 · minimum image side 1,500 px· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 91% |
| 7 | DeepSeek V4.1 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 89.6% |
| 8 | DeepSeek V4.1 FlashDeepSeek V4.1 launch chart · exact public value · setting not further specified · with tools· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 89.6% |
| 9 | DeepSeek V4.1 Flashwith tools · Claude Code · 512K · pass@1· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 89.6% |
| 10 | Particle 1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 89.2% |
| 11 | GPT-5.6 SolDeepSeek V4.1 launch chart · exact public value · setting not further specified · with tools· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 88.9% |
| 12 | Kimi K3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 85.7% |
| 13 | Kimi K3DeepSeek V4.1 launch chart · exact public value · setting not further specified · with tools· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 85.7% |
| 14 | Kimi K3Python tool · three-run average · max effort· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 85.7% |
| 15 | Qwen 3.8 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 85.6% |
| 16 | GPT 5.5xhigh · with code execution · 388 questions · gpt-oss-120b high judge· Reported by Meta, Meta Superintelligence Labs· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 83.6% |
| 17 | Claude Opus 4.8max · with code execution · 388 questions · gpt-oss-120b high judge· Reported by Meta, Meta Superintelligence Labs· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 81.2% |
| 18 | Muse Spark Open· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 80.2% |
| 19 | Muse Spark 1.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 76.3% |
| 20 | Muse Spark 1.1Meta Model API · xhigh · with code execution · 388 questions · gpt-oss-120b high judge· Reported by Meta, Meta Superintelligence Labs· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 76.3% |
| 21 | Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 73.7% |
| 22 | Qwen3.7 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 70.4% |
| 23 | Kimi K2.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 68.5% |
| 24 | Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 62.9% |
| 25 | GLM 5.3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 53.4% |
| 26 | GLM 5.3 FlashZ.ai Flash设置· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 53.4% |
| 27 | Gemini 3.1 Pro Previewhigh · with code execution · 388 questions · gpt-oss-120b high judge· Reported by Meta, Meta Superintelligence Labs· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 51.5% |
| 28 | Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 44.6% |
| 29 | Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 40.2% |
| 30 | Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 38.7% |
| 31 | Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 38.4% |
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 · with code execution · 388 questions · gpt-oss-120b high judge· Reported by Meta, Meta Superintelligence Labs· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 39.9% |
| Qwen3.8-2.4T-A95Blifecycle-page core-benchmark claim · CI setting not stated· Reported by Alibaba Cloud Model Studio· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 82% |
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