Benchmark
IFBench
Instruction following benchmarks measure how closely models follow instructions. Scores are percentages. Higher is better.
- Models measured
- 51
- Scores recorded
- 70
- Sources
- 2
- IQ weight
- 1.40
Score distribution
- 71.6%
- Mean
- 74.2%
- Median
- 11.2%
- Std dev
- 59.2%
- 10th percentile
- 81.3%
- 90th percentile
- 21%
- Min
This benchmark has a weight of 1.40 for chat models, measured over 51 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 | Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 70.2% |
| 52 | MiniMax M2.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 70% |
| 53 | MiniMax M2.5official appendix· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 70% |
| 54 | GPT OSS 120Bhigh· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 69.5% |
| 55 | Mai Thinking 1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 69% |
| 56 | Mistral Medium 3.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 69% |
| 57 | Step 3.5 FlashStep 3.5 technical report · Table 5 · vanilla· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 67.4% |
| 58 | Qwen3.5 9B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 64.5% |
| 59 | Claude Fable 5Qwen3.8 官方模型卡对照表· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 63.5% |
| 60 | Claude Opus 4.6Qwen3.8 Omni Flash 官方发布表 · max effort· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 62.5% |
| 61 | Claude Opus 4.8Qwen3.8 官方模型卡对照表· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 62.2% |
| 62 | Qwen3.5 4B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 59.2% |
| 63 | LFM2.5 2.6B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 59.2% |
| 64 | Step 3.5 FlashStep 3.5 technical report · Table 5 · PaCoRe· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 56.8% |
| 65 | Qwen3.5 Omni PlusQwen3.5-Omni release · no-thinking setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 52.6% |
| 66 | Trinity Large ThinkingTrinity-Large-Thinking Model Card· Reported by Arcee AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 52.3% |
| 67 | Mistral Smalllatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 48% |
| 68 | Qwen3.5 2B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 41.3% |
| 69 | Qwen3.5 Omni FlashQwen3.5-Omni release · no-thinking setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 38.4% |
| 70 | Qwen3.5 0.8B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 21% |
Showing 51–70 of 70 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.