AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
Arena Hard
Arena-Hard-Auto is an automatic evaluation benchmark for instruction-tuned LLMs consisting of 500 challenging real-world prompts curated by BenchBuilder. It includes open-ended software engineering problems, mathematical questions, and creative writing tasks. The benchmark uses LLM-as-a-Judge methodology with GPT-4.1 and Gemini-2.5 as automatic judges to approximate human preference. Arena-Hard achieves 98.6% correlation with human preference rankings and provides 3x higher separation of model performances compared to MT-Bench, making it highly effective for distinguishing between models of similar quality.
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- Not recorded
- Benchmark release
- Not recorded
- Collected
- 2026-08-17
- Modality
- text
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 26
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Qwen3 235B A22B | 0.956 | Not recorded | Not recorded | 2025-04-29 · model_announcement | LLM Stats |
| Qwen3 32B | 0.938 | Not recorded | Not recorded | 2025-04-29 · model_announcement | LLM Stats |
| Qwen3 30B A3B | 0.91 | Not recorded | Not recorded | 2025-04-29 · model_announcement | LLM Stats |
| Llama-3.3 Nemotron Super 49B v1 | 0.883 | Not recorded | Not recorded | 2025-03-18 · model_announcement | LLM Stats |
| Mistral Small 3 24B Instruct | 0.876 | Not recorded | Not recorded | 2025-01-30 · model_announcement | LLM Stats |
| Qwen2.5 72B Instruct | 0.812 | Not recorded | Not recorded | 2024-09-19 · model_announcement | LLM Stats |
| Phi 4 Reasoning Plus | 0.79 | Not recorded | Not recorded | 2025-04-30 · model_announcement | LLM Stats |
| DeepSeek-V2.5 | 0.762 | Not recorded | Not recorded | 2024-05-08 · model_announcement | LLM Stats |
| Phi 4 | 0.754 | Not recorded | Not recorded | 2024-12-12 · model_announcement | LLM Stats |
| Phi 4 Reasoning | 0.733 | Not recorded | Not recorded | 2025-04-30 · model_announcement | LLM Stats |
| Ministral 8B Instruct | 0.709 | Not recorded | Not recorded | 2024-10-16 · model_announcement | LLM Stats |
| Jamba 1.5 Large | 0.654 | Not recorded | Not recorded | 2024-08-22 · model_announcement | LLM Stats |
| Mistral Small 4 | 0.583 | Not recorded | Not recorded | 2026-03-16 · model_announcement | LLM Stats |
| Granite 3.3 8B Instruct | 0.5756 | Not recorded | Not recorded | 2025-04-16 · model_announcement | LLM Stats |
| Granite 3.3 8B Base | 0.5756 | Not recorded | Not recorded | 2025-04-16 · model_announcement | LLM Stats |
| MiniStral 3 (14B Instruct 2512) | 0.551 | Not recorded | Not recorded | 2025-12-04 · model_announcement | LLM Stats |
| Mistral Large 3 | 0.551 | Not recorded | Not recorded | 2025-09-01 · model_announcement | LLM Stats |
| Qwen2.5 7B Instruct | 0.52 | Not recorded | Not recorded | 2024-09-19 · model_announcement | LLM Stats |
| Ministral 3 (8B Instruct 2512) | 0.509 | Not recorded | Not recorded | 2025-12-04 · model_announcement | LLM Stats |
| Jamba 1.5 Mini | 0.461 | Not recorded | Not recorded | 2024-08-22 · model_announcement | LLM Stats |
| Mistral Small 3.2 24B Instruct | 0.431 | Not recorded | Not recorded | 2025-06-20 · model_announcement | LLM Stats |
| Phi-3.5-MoE-instruct | 0.379 | Not recorded | Not recorded | 2024-08-23 · model_announcement | LLM Stats |
| Phi-3.5-mini-instruct | 0.37 | Not recorded | Not recorded | 2024-08-23 · model_announcement | LLM Stats |
| Phi 4 Mini | 0.328 | Not recorded | Not recorded | 2025-02-01 · model_announcement | LLM Stats |
| Ministral 3 (3B Instruct 2512) | 0.305 | Not recorded | Not recorded | 2025-12-04 · model_announcement | LLM Stats |
| IBM Granite 4.0 Tiny Preview | 0.267 | Not recorded | Not recorded | 2025-05-02 · model_announcement | LLM Stats |