GPT-4.1 nano

GPT-4.1 nano is a non-reasoning model from OpenAI in the GPT-4.1 family. 24 benchmarks count toward its score, in 7 categories.

availableShows if the model has enough results for an index.
IndexOverall score. 50 is the middle.25.5 ±3.8
CoverageShare of the index weight with results.95%
SpeedOutput tokens per second.39/s
Input / 1MUS dollars per 1M input tokens.$0.1 batch $0.05
Output / 1MUS dollars per 1M output tokens.$0.4 batch $0.2 US dollars per 1M output tokens in a batch.
ContextMaximum tokens in one request.1.05M
EloLMArena rating and rank.1285 (#250)

50 is the middle of the board. The range shows the doubt in the index. Batch work costs less.

6,103 votes. Elo shows what people prefer. It does not change the score.

CapabilitiesScore per category. 50 is the middle.

50 is the middle
AgenticMulti-step tasks with tools.
23.4
CodingCode writing and repair.
25.0
ReasoningLogic problems and puzzles.
31.9
MultimodalTasks with images and text.
16.5
KnowledgeFacts and expert knowledge.
26.4
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
26.1
MathMath problems.
30.0

Results

24 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result on the index scale.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
Instruction-Following EvalInstruction83.2%30.6Jeffrey Zhou et al.
MATH 500Math80.2%31.49 Jan 2026Vals AI
Massive Multitask Language UnderstandingKnowledge80.1%Dan Hendrycks et al.
MATH level 5Math70.0%33.1Epoch AI
MGSMMultilingual69.3%9 Jan 2026Vals AI
MMLU ProKnowledge63.5%20.41 Sept 2026Vals AI
MMMU ProMultimodal55.1%16.91 Sept 2026Vals AI
Artificial Analysis GPQA DiamondKnowledge51.2%21.0Artificial Analysis
GPQA DiamondKnowledge50.8%25.11 Sept 2026Vals AI
Graduate-Level Google-Proof Q&AKnowledge50.3%24.7David Rein et al.
GPQA diamondKnowledge48.9%23.4Epoch AI
LiveCodeBenchCoding42.7%23.21 Sept 2026Vals AI
Artificial Analysis MMMU-ProMultimodal40.1%16.1Artificial Analysis
Artificial Analysis IFBenchInstruction32.0%21.6Artificial Analysis
OTIS Mock AIME 2024-2025Math28.9%27.8Epoch AI
AIMEMath26.5%26.016 Apr 2026Vals AI
Artificial Analysis Long Context ReasoningReasoning20.3%22.3Artificial Analysis
τ²-Bench Tool-Agent-User EvaluationAgentic17.3%11.2Victor Barres et al.
Artificial Analysis Omniscience AccuracyKnowledge13.7%30.8Artificial Analysis
Artificial Analysis Coding IndexCoding11.1%26.8Artificial Analysis
Artificial Analysis Intelligence IndexKnowledge7.8%32.2Artificial Analysis
SimpleQA VerifiedKnowledge6.0%27.1Epoch AI
Artificial Analysis Humanity's Last ExamKnowledge3.8%28.7Artificial Analysis
FrontierMath-2025-02-28-PrivateMath1.0%31.6Epoch AI
GDPval-AA normalizedAgentic0.0%35.6Artificial Analysis
Critical Physics TasksReasoning0.0%38.4Artificial Analysis
ARC-AGI-1 (semi-private)Reasoning0.0%27.2ARC Prize Foundation
ARC-AGI-2 (semi-private)Reasoning0.0%39.7ARC Prize Foundation

24 benchmarks count, from 26 of 28 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authorsOpenRouter, collected directlyNo licence statedVals AI, collected directlyNo licence stated. Read from the public leaderboard and credited to Vals AIEpoch AI, collected directlyCC BY — free to use and redistribute with attributionARC Prize Foundation, collected directlyNo licence stated. Their terms ask for written permission before commercial use

Same level, lower price

Qwen3.8-Flash-Next66.4 · Freedots3-note Preview65.5 · FreeApodex 1.1 Mini59.1 · Free

More from OpenAI

GPT-6 Astra83.5GPT-5.6 Sol76.7GPT-5.6 Terra73.4GPT-6 Sol76.9GPT-5.572.3