benchmark evidence
IFEval (Open LLM Leaderboard)
Open LLM Leaderboard v2 — IFEval (Open LLM Leaderboard).
activeupstream source ->
winner on IFEval (Open LLM Leaderboard)
OpenAI: o3 Mini93.9
direct benchmark result, not a broad vertical composite | source row dated 2000-01-01
scored on 2026-05-08 · stale source data (62d)
latest mapped results | top 20
| # | Model | Score | Evidence | Tested |
|---|---|---|---|---|
| 1 | OpenAI: o3 Mini | 93.9 | model-only independent_benchmark | 2000-01-01 |
| 2 | Meta: Llama 3.3 70B Instruct | 88.0 | model-only leaderboard | 2026-05-08 |
| 3 | OpenAI: GPT-4.1 | 87.4 | model-only independent_benchmark | 2000-01-01 |
| 4 | Mistral Large | 81.0 | model-only leaderboard | 2026-05-08 |
| 5 | Mistral: Mistral Nemo | 58.8 | model-only leaderboard | 2026-05-08 |
| 6 | Mistral: Mistral Small 4 | 57.7 | model-only leaderboard | 2026-05-08 |
what this result means
Open LLM Leaderboard v2 — IFEval (Open LLM Leaderboard).
This benchmark contributes direct public evidence. Read its scope before generalizing the result.
A win here is a win on IFEval (Open LLM Leaderboard). Broad task pages require independent corroboration before naming a general winner.
source record
category: overall
metric: accuracy
matched models: 6
latest source date: 2026-05-08
direction: higher is better