GPT-4o mini: benchmark scores, price and ranking
GPT-4o mini from OpenAI ranks #459 of 743 LLMs on the LLMs Tiger aggregate benchmark score (47.1), based on 3 benchmark results captured up to 2026-10-14.
- Organisation
- OpenAI
- Type
- Fast / low-cost (flash) model
- Open weights
- No
- Released
- 2024-07-18 (source: curated)
- Context window
- 128,000 tokens
- Cheapest API price
- $0.150 in / $0.600 out per million tokens (via azure, observed 2026-10-14T22:47Z)
- Aggregate rank
- #459 of 743 (score 47.1)
Relative to other models, GPT-4o mini is strongest on Aider Code Editing (#46 of 92) and weakest on ARC-AGI-2 (#82 of 87).
Across the 3 benchmarks where at least ten models are scored, GPT-4o mini is in the top 10% on 0 and in the top half on 1.
Its cheapest listed input price, $0.150 per million tokens, is lower than that of 72% of the 427 models with a listed price.
GPT-4o mini benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Aider Code Editing | 55.6% | #46 of 92 | Aider Aider Code Editing leaderboard | 2026-10-14 |
| Epoch ECI | 127 | #108 of 204 | Epoch AI Benchmarking Hub | 2026-10-14 |
| ARC-AGI-2 | 0.0% | #82 of 87 | ARC Prize official leaderboard | 2026-10-14 |
About GPT-4o mini
GPT-4o mini is a smaller, lower-cost model from OpenAI. It was released on 2024-07-18, according to the developer's announcement. It accepts up to 128,000 tokens of input at once. The cheapest API listing we track charges $0.150 per million input tokens and $0.600 per million output tokens, through azure. We hold 3 benchmark results for it across 3 areas, and none is in the top tenth of its board.
Where GPT-4o mini stands
On our aggregate score, GPT-4o mini is #459 of 743 ranked models, in the lower half. Its score is 47.1; the scale is centred on 50, so it sits 2.9 points below the typical model. That beats 38% of the ranked field. Among the 88 ranked OpenAI models it is #60. The next one up is GPT-4o at 47.2. The next one down is gpt-5.5-xhigh (codex-harness) at 47.1.
GPT-4o mini, benchmark by benchmark
Aider Code Editing puts GPT-4o mini at 55.6%, #46 of 92. That beats 50% of the models tested, but 28.6 points short of Claude 3.5-Sonnet-20241022 (84.2%). The results either side are gpt-3.5-turbo-1106 (56.1%) and qwen2-72b-instruct (55.6%). It covers Aider official benchmark. The median score on this board is also 55.6%. Source: Aider Aider Code Editing leaderboard, captured 2026-10-14.
GPT-4o mini lands below the middle on Epoch ECI: 127, #108 of 204, with 52% of the field scoring higher. Qwen 3.8 Max leads at 156; the closest result above is Gemini 1.5 Pro (May 2024) at 127. It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so GPT-4o mini is 1 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-14.
ARC-AGI-2 is a weak spot. GPT-4o mini scores 0.0%, #82 of 87, behind 93% 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-4o mini is 22.8 points below it. Source: ARC Prize official leaderboard, captured 2026-10-14.
Strengths and weaknesses
GPT-4o mini has too few results on boards with ten or more models to say where it is strong or weak. Treat any single score as a data point, not a verdict.
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so GPT-4o mini costs less than the typical listing. Models that score within 1.5 points or better and cost less: DeepSeek V4.1 Flash (high) ($0.010, 49.7), Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on qwen3-235b-a22b ($0.180) and codestral-2405 ($0.200).
Release history
The OpenAI model released before it was GPT-4o (May 2024) on 2024-05-13, which scores 44.3. The next one was gpt-4o-mini-2024-07-18 on 2024-07-18, at 38.3.
Reading these numbers
The 3 scores on this page come from 3 sources: ARC Prize official leaderboard (1), Aider Aider Code Editing leaderboard (1), Epoch AI Benchmarking Hub (1). 2 of them come from an official leaderboard and 1 from datasets or third-party runs. With 3 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #456 GPT-4o (47.2)
- #457 openhands-lm-32b-v0.1 (47.2)
- #458 qwen3.7-max-20260517 (47.2)
- #460 Qwen1.5-110B (47.1)
- #461 granite-4.1-8b (47.1)
- #462 gpt-5.5-xhigh (codex-harness) (47.1)
More from OpenAI
- GPT-6 Astra (max) (#2, 63.9)
- GPT-6.1 Sol (max) (#3, 62.0)
- GPT-5.6 Sol (max) (#8, 59.9)
- GPT-6 Sol (max) (#9, 59.9)
- GPT-5.5 (xhigh) (#11, 57.8)
- GPT-5.6 Terra (max) (#12, 57.6)
Compare it on the live leaderboard → · How the aggregate score works