GPQA Diamond ↗50.76 %
GPT 4.1 Nano · GPQA Diamond · Accuracy ↗
1 more reported result
48.93% · GPT-4.1 nano · GPQA diamond · Best score (across scorers) · % · Epoch AI · GPQA diamond ↗
OpenAI / MODEL EVIDENCE
GPT-4.1 nano
28 benchmarks · 31 observations · 31 sources · released 2025-04-14
Scores at a glance
28 benchmarks · large dot: GPT-4.1 nano; small dots: closest models where reported
GPT-4.1 nano · FrontierMath-2025-02-28-Private · Best score (across scorers) · % ↗
GPT-4.1 nano · MATH level 5 · Best score (across scorers) · % ↗
GPT-4.1 nano · OTIS Mock AIME 2024-2025 · Best score (across scorers) · % ↗
GPT-4.1 nano · SimpleQA Verified · Best score (across scorers) · % ↗
GPT-4.1 nano · Chess Puzzles · Best score (across scorers) · % ↗
GPT-4.1 nano · Aider coding benchmarks · Polyglot · percent correct ↗
1 more reported result
8.9% · gpt-4.1-nano · Aider coding benchmarks · Polyglot · percent correct · Aider code editing benchmark ↗
GPT-4.1 nano · ARC-AGI · Score · % ↗
GPT-4.1 nano · Fiction.LiveBench · 16k token score · % ↗
WeirdML (v2) ↗18.98%
GPT-4.1 nano · WeirdML · Accuracy · % ↗
GPT-4.1 nano · ARC-AGI-2 · Score · % ↗
CritPt ↗0%
GPT-4.1 nano · CritPt · Accuracy · % ↗
LMCA ↗5.46%
GPT-4.1 nano · LMCA · Score · % ↗
DTBench ↗52.53%
GPT-4.1 nano · DTBench · Accuracy · % ↗
SciCode ↗25.93%
GPT-4.1 nano · SciCode · Score · % ↗
Epoch Capabilities Index (ECI) ↗129.54 ECI
GPT-4.1 nano · General ECI · 26 October 2026 fit ↗
LegalBench ↗61.06 %
GPT 4.1 Nano · LegalBench · Accuracy ↗
CorpFin v2 ↗42.08 %
GPT 4.1 Nano · CorpFin · Accuracy ↗
MortgageTax & TaxEval v2 ↗52.82 %
GPT 4.1 Nano · MortgageTax · Accuracy ↗
1 more reported result
60.75 % · GPT 4.1 Nano · TaxEval · Accuracy · Vals AI · TaxEval ↗
MedQA (USMLE) ↗68.22 %
GPT 4.1 Nano · MedQA · Accuracy ↗
AIME 2024–2025 · Vals ↗26.46 %
GPT 4.1 Nano · AIME · Accuracy ↗
MATH-500 ↗80.2 %
GPT 4.1 Nano · MATH 500 · Accuracy ↗
MGSM (Multilingual GSM) ↗69.27 %
GPT 4.1 Nano · MGSM · Accuracy ↗
MMLU-Pro ↗63.48 %
GPT 4.1 Nano · MMLU Pro · Accuracy ↗
MMMU-Pro ↗55.05 %
GPT 4.1 Nano · MMMU Pro · Accuracy ↗
LiveCodeBench ↗42.72 %
GPT 4.1 Nano · LiveCodeBench · Accuracy ↗
GPT-4.1 nano · Scale Labs · Score ↗
VISTA ↗26.55%
GPT-4.1 nano · Scale Labs · Score ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
Llama 4 Scout →Meta
14 of 18 shared benchmark comparisons
11 of 18 shared benchmark comparisons
Gemini 1.5 Pro (002) →Google
11 of 18 shared benchmark comparisons
How similarity is measured
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- Aider code editing benchmark ↗
- Aider LLM Leaderboards — Polyglot coding benchmark ↗
- ARC Prize - Leaderboard ↗
- SciCode Benchmark | Artificial Analysis ↗
- DTBench — Conceptual Reasoning Index ↗
- LMCA — Conceptual Reasoning Index ↗
- ARC-AGI-2 ↗
- Chess Puzzles ↗
- CritPt v1 ↗
- FrontierMath Tiers 1-3 (v1, old) ↗
- GPQA Diamond ↗
- MATH Level 5 ↗
- OTIS Mock AIME 2024-2025 ↗
- SimpleQA Verified ↗
- AI benchmarks & capabilities ↗
- Fiction.liveBench — March 14, 2025 benchmark release ↗
- WeirdML ↗
- Scale Labs — evaluation methodology and results ↗
- Scale Labs — evaluation methodology and results ↗
- AIME — evaluation methodology and results ↗
- CorpFin — evaluation methodology and results ↗
- GPQA Diamond — evaluation methodology and results ↗
- LiveCodeBench — evaluation methodology and results ↗
- LegalBench — evaluation methodology and results ↗
- MATH 500 — evaluation methodology and results ↗
- MedQA — evaluation methodology and results ↗
- MGSM — evaluation methodology and results ↗
- MMLU Pro — evaluation methodology and results ↗
- MMMU Pro — evaluation methodology and results ↗
- MortgageTax — evaluation methodology and results ↗
- TaxEval — evaluation methodology and results ↗
Names used in source tables
GPT 4.1 Nano · GPT-4.1 nano · gpt-4.1-nano