LLMs TigerLive LLM benchmarks

GPT-4.1 mini: benchmark scores, price and ranking

GPT-4.1 mini from OpenAI ranks #689 of 743 LLMs on the LLMs Tiger aggregate benchmark score (43.0), based on 16 benchmark results captured up to 2026-10-13.

Organisation
OpenAI
Type
Fast / low-cost (flash) model
Open weights
No
Released
2025-04-14 (source: curated)
Context window
1,047,576 tokens
Cheapest API price
$0.400 in / $1.60 out per million tokens (via azure, observed 2026-10-13T19:47Z)
Aggregate rank
#689 of 743 (score 43.0)

Relative to other models, GPT-4.1 mini is strongest on Epoch ECI (#72 of 204) and weakest on SimpleQA Verified (#63 of 69).

Across the 16 benchmarks where at least ten models are scored, GPT-4.1 mini is in the top 10% on 0 and in the top half on 2.

Its cheapest listed input price, $0.400 per million tokens, is lower than that of 53% of the 427 models with a listed price.

GPT-4.1 mini benchmark results

GPT-4.1 mini benchmark scores, ranked against all models measured on each benchmark
BenchmarkScoreRankSourceCaptured
Epoch ECI135#72 of 204Epoch AI Benchmarking Hub2026-10-13
DTBench68.8%#73 of 146Epoch AI Benchmarking Hub2026-10-13
GPQA Diamond65.8%#154 of 275Epoch AI Benchmarking Hub2026-10-13
OTIS Mock AIME44.7%#110 of 189Epoch AI Benchmarking Hub2026-10-13
SciCode40.4%#62 of 106Epoch AI Benchmarking Hub2026-10-13
Chess Puzzles7.0%#72 of 122Epoch AI Benchmarking Hub2026-10-13
Aider Polyglot32.4%#30 of 49Aider polyglot leaderboard2026-10-13
WeirdML37.6%#70 of 109Epoch AI Benchmarking Hub2026-10-13
LMCA21.1%#71 of 108Epoch AI Benchmarking Hub2026-10-13
CritPt0.0%#93 of 115Epoch AI Benchmarking Hub2026-10-13
Fiction.liveBench44.4%#39 of 47Epoch AI Benchmarking Hub2026-10-13
Mystery Games7.0%#49 of 59Epoch AI Benchmarking Hub2026-10-13
SWE-bench Verified23.9%#63 of 73SWE-bench Verified leaderboard2026-10-13
ARC-AGI-20.0%#79 of 87ARC Prize official leaderboard2026-10-13
FrontierMath T1-36.7%#62 of 68Epoch AI Benchmarking Hub2026-10-13
SimpleQA Verified12.7%#63 of 69Epoch AI Benchmarking Hub2026-10-13

About GPT-4.1 mini

GPT-4.1 mini is a smaller, lower-cost model from OpenAI. It was released on 2025-04-14, according to the developer's announcement. It accepts up to 1,047,576 tokens of input at once. The cheapest API listing we track charges $0.400 per million input tokens and $1.60 per million output tokens, through azure. We hold 16 benchmark results for it across 4 areas, and none is in the top tenth of its board.

Where GPT-4.1 mini stands

On our aggregate score, GPT-4.1 mini is #689 of 743 ranked models, in the lower half. Its score is 43.0; the scale is centred on 50, so it sits 7.0 points below the typical model. That beats 7% of the ranked field. Among the 88 ranked OpenAI models it is #80. The next one up is GPT-4 (Mar 2023) at 43.7. The next one down is GPT-3.5 at 43.0.

GPT-4.1 mini, benchmark by benchmark

Epoch ECI puts GPT-4.1 mini at 135, #72 of 204. That beats 65% of the models tested, but 21 points short of Qwen 3.8 Max (156). The results either side are Gemini 2.0 Pro (135) and o1-preview (135). It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so GPT-4.1 mini is 8 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

On DTBench, GPT-4.1 mini reaches 68.8%. It ranks #73 of 146, ahead of 50% of the field, and 30.1 points behind Claude Opus 5.5 (max) at 98.9%. The results either side are qwen3-30b-a3b-thinking-2507 (69.3%) and o3-mini (high) (68.8%). It covers dynamic tool-use benchmark. The median score on this board is also 68.8%. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

GPT-4.1 mini lands below the middle on GPQA Diamond: 65.8%, #154 of 275, with 56% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is claude-3-7-sonnet-20250219 at 66.0%. It covers expert-level science questions. The board median is 71.7%, so GPT-4.1 mini is 5.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

GPT-4.1 mini lands below the middle on OTIS Mock AIME: 44.7%, #110 of 189, with 58% of the field scoring higher. Claude Fable 5.1 (max) leads at 100.0%; the closest result above is o1-mini (high) at 46.9%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so GPT-4.1 mini is 13.1 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

GPT-4.1 mini lands below the middle on SciCode: 40.4%, #62 of 106, with 58% of the field scoring higher. Claude Opus 5.5 (max) leads at 66.9%; the closest result above is DeepSeek-V3.1-Terminus at 40.6%. It covers scientific research code. The board median is 44.3%, so GPT-4.1 mini is 3.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

GPT-4.1 mini lands below the middle on Chess Puzzles: 7.0%, #72 of 122, with 58% of the field scoring higher. GPT-6 Astra (max) leads at 72.0%; the closest result above is claude-opus-4-1-20250805 at 7.0%. It covers chess tactics puzzles. The board median is 12.5%, so GPT-4.1 mini is 5.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

SWE-bench Verified is a weak spot. GPT-4.1 mini scores 23.9%, #63 of 73, behind 85% of the models measured. The leader, Claude Opus 4.7 (max), reaches 83.5%. It covers real GitHub issues resolved. The board median is 56.4%, so GPT-4.1 mini is 32.5 points below it. Source: SWE-bench Verified leaderboard, captured 2026-10-13.

ARC-AGI-2 is a weak spot. GPT-4.1 mini scores 0.0%, #79 of 87, behind 90% of the models measured. The leader, GPT-6 Astra (max), reaches 95.0%. It covers abstract reasoning, ARC Prize public eval set. The board median is 22.8%, so GPT-4.1 mini is 22.8 points below it. Source: ARC Prize official leaderboard, captured 2026-10-13.

FrontierMath T1-3 is a weak spot. GPT-4.1 mini scores 6.7%, #62 of 68, behind 90% of the models measured. The leader, GPT-6 Astra (max), reaches 93.7%. It covers research-level maths, tiers 1-3. The board median is 55.6%, so GPT-4.1 mini is 48.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

SimpleQA Verified is a weak spot. GPT-4.1 mini scores 12.7%, #63 of 69, behind 90% of the models measured. The leader, gemini-4-argon-high, reaches 76.0%. It covers short factual questions. The board median is 41.0%, so GPT-4.1 mini is 28.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

The full table above also lists the other 6 results, including boards with fewer than ten models, where a rank says little.

Strengths and weaknesses

Software engineering: uneven, ahead of 31% of the field on average across 3 benchmarks. Its best board here is SciCode (#62 of 106) and its weakest is SWE-bench Verified (#63 of 73). Reasoning, maths and science: weak, ahead of 25% of the field on average across 5 benchmarks. Its best board here is GPQA Diamond (#154 of 275) and its weakest is FrontierMath T1-3 (#62 of 68). General knowledge and chat: uneven, ahead of 31% of the field on average across 7 benchmarks. Its best board here is Epoch ECI (#72 of 204) and its weakest is SimpleQA Verified (#63 of 69).

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so GPT-4.1 mini costs less than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on Mistral Large 3 ($0.500) and Mixtral-8x22B-Instruct-v0.1 ($0.600).

Release history

The OpenAI model released before it was GPT-4.1 on 2025-04-14, which scores 44.9. The next one was GPT-4.1 nano on 2025-04-14, at 38.7.

Reading these numbers

The 16 scores on this page come from 4 sources: Epoch AI Benchmarking Hub (13), ARC Prize official leaderboard (1), Aider polyglot leaderboard (1), SWE-bench Verified leaderboard (1). 3 of them come from an official leaderboard and 13 from datasets or third-party runs.

Models ranked nearby

More from OpenAI

Compare it on the live leaderboard → · How the aggregate score works