Benchmark
ZEROBench
Scores are percentages. Higher is better.
- Models measured
- 84
- Scores recorded
- 90
- Sources
- 3
- IQ weight
- 2.09
Score distribution
- 5.4%
- Mean
- 2%
- Median
- 7.8%
- Std dev
- 0%
- 10th percentile
- 13.4%
- 90th percentile
- 0%
- Min
This benchmark has a weight of 2.09 for chat models, measured over 84 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 |
|---|---|---|
| 51 | Grok 4· ZeroBench | 1.4% |
| 52 | Claude Opus 4· ZeroBench | 1.2% |
| 53 | Claude Sonnet 4.5· ZeroBench | 1.2% |
| 54 | GPT-5 nanohigh reasoning· ZeroBench | 1% |
| 55 | Qwen3.5 Omni FlashQwen3.5-Omni release · published setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1% |
| 56 | GPT 4.1· ZeroBench | 0.6% |
| 57 | DeepSeek V4.1 Flash 1017· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.51% |
| 58 | Muse Spark Open· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.5% |
| 59 | DeepSeek V4.1 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.49% |
| 60 | Hy4 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.458% |
| 61 | Kimi K3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.41% |
| 62 | Claude Sonnet 3.7· ZeroBench | 0.4% |
| 63 | Llama 4 Maverick· ZeroBench | 0.4% |
| 64 | Kimi K3.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.39% |
| 65 | DeepSeek V4 Flash Vision Exp· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.35% |
| 66 | Muse Spark· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.33% |
| 67 | Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.18% |
| 68 | Inkling 2 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.17% |
| 69 | Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.11% |
| 70 | Kimi K2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.11% |
| 71 | Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.1% |
| 72 | Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.09% |
| 73 | Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.08% |
| 74 | Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 0.07% |
| 75 | Qwen3 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 0.04% |
| 76 | Claude 3 Haiku· ZeroBench | 0% |
| 77 | Claude 3 Opus· ZeroBench | 0% |
| 78 | Claude 3 Sonnet· ZeroBench | 0% |
| 79 | Claude 3.5 Sonnet· ZeroBench | 0% |
| 80 | Claude 3.5 Sonnet v2· ZeroBench | 0% |
| 81 | Gemini 1.5 Flash· ZeroBench | 0% |
| 82 | Gemini 1.5 Pro· ZeroBench | 0% |
| 83 | GPT 4o· ZeroBench | 0% |
| 84 | GPT-4o mini· ZeroBench | 0% |
| 85 | llama-3.2-90b· ZeroBench | 0% |
| 86 | o1· ZeroBench | 0% |
| 87 | O1 Pro· ZeroBench | 0% |
| 88 | Pixtral Large· ZeroBench | 0% |
| 89 | Qwen2-VL (72B) Instruct· ZeroBench | 0% |
| 90 | Reka Edge· ZeroBench | 0% |
Showing 51–90 of 90 results.
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.