GPT-4o (Aug 2024): benchmark scores, price and ranking

GPT-4o (Aug 2024) from OpenAI ranks #709 of 743 LLMs on the LLMs Tiger aggregate benchmark score (42.2), based on 7 benchmark results captured up to 2026-10-13.

Organisation

OpenAI

Type

Frontier model

Open weights

No

Released

2024-08-06 (source: epoch)

Cheapest API price

$2.50 in / $10.00 out per million tokens (via azure, observed 2026-10-13T20:47Z)

Aggregate rank

#709 of 743 (score 42.2)

Relative to other models, GPT-4o (Aug 2024) is strongest on Epoch ECI (#96 of 204) and weakest on FrontierMath T1-3 (#67 of 68).

Across the 7 benchmarks where at least ten models are scored, GPT-4o (Aug 2024) is in the top 10% on 0 and in the top half on 2.

Its cheapest listed input price, $2.50 per million tokens, is lower than that of 15% of the 427 models with a listed price.

GPT-4o (Aug 2024) benchmark results

About GPT-4o (Aug 2024)

GPT-4o (Aug 2024) is a frontier model from OpenAI. It was released on 2024-08-06, according to Epoch AI. The cheapest API listing we track charges $2.50 per million input tokens and $10.00 per million output tokens, through azure. We hold 7 benchmark results for it across 2 areas, and none is in the top tenth of its board.

Where GPT-4o (Aug 2024) stands

On our aggregate score, GPT-4o (Aug 2024) is #709 of 743 ranked models, in the lower half. Its score is 42.2; the scale is centred on 50, so it sits 7.8 points below the typical model. That beats 5% of the ranked field. Among the 88 ranked OpenAI models it is #84. The next one up is GPT-4o (Nov 2024) at 42.3. The next one down is GPT-4 (Jun 2023) at 41.2.

GPT-4o (Aug 2024), benchmark by benchmark

Epoch ECI puts GPT-4o (Aug 2024) at 129, #96 of 204. That beats 53% of the models tested, but 28 points short of Qwen 3.8 Max (156). The results either side are GPT-4o (Nov 2024) (129) and Llama 3.1-405B (129). It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so GPT-4o (Aug 2024) is 1 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

On Chess Puzzles, GPT-4o (Aug 2024) reaches 13.0%. It ranks #59 of 122, ahead of 52% of the field, and 59.0 points behind GPT-6 Astra (max) at 72.0%. The results either side are MiniMax-M3 (14.0%) and Qwen3.5 397B-A17B (13.0%). It covers chess tactics puzzles. The board median is 12.5%, so GPT-4o (Aug 2024) is 0.5 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

GPT-4o (Aug 2024) lands below the middle on GPQA Diamond: 49.2%, #187 of 275, with 68% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is o1-preview at 50.3%. It covers expert-level science questions. The board median is 71.7%, so GPT-4o (Aug 2024) is 22.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

GPT-4o (Aug 2024) lands below the middle on SimpleQA Verified: 26.0%, #52 of 69, with 74% of the field scoring higher. gemini-4-argon-high leads at 76.0%; the closest result above is grok-4.20-0309-reasoning at 30.2%. It covers short factual questions. The board median is 41.0%, so GPT-4o (Aug 2024) is 15.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

GPT-4o (Aug 2024) lands below the middle on OTIS Mock AIME: 6.4%, #151 of 189, with 79% of the field scoring higher. Claude Fable 5.1 (max) leads at 100.0%; the closest result above is Claude 3.5 Sonnet (Jun 2024) at 6.5%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so GPT-4o (Aug 2024) is 51.4 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

SimpleBench is a weak spot. GPT-4o (Aug 2024) scores 17.8%, #59 of 61, behind 95% of the models measured. The leader, Claude Fable 5 (max), reaches 81.9%. It covers trick questions that test common sense. The board median is 41.4%, so GPT-4o (Aug 2024) is 23.6 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

FrontierMath T1-3 is a weak spot. GPT-4o (Aug 2024) scores 0.4%, #67 of 68, behind 97% 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-4o (Aug 2024) is 55.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

Reasoning, maths and science: weak, ahead of 14% of the field on average across 4 benchmarks. Its best board here is GPQA Diamond (#187 of 275) and its weakest is FrontierMath T1-3 (#67 of 68). General knowledge and chat: uneven, ahead of 43% of the field on average across 3 benchmarks. Its best board here is Epoch ECI (#96 of 204) and its weakest is SimpleQA Verified (#52 of 69).

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so GPT-4o (Aug 2024) costs more 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 claude-3-sonnet-20240229 ($3.00) and Llama-3.1-405B-Instruct ($3.50).

Release history

The OpenAI model released before it was gpt-4o-2024-08-06 on 2024-08-06, which scores 49.5. The next one was o1-mini-2024-09-12 on 2024-09-12, at 44.8.

Reading these numbers

The 7 scores on this page come from 1 source: Epoch AI Benchmarking Hub (7). No official leaderboard supplied any of them, so treat them as third-party measurements. With 7 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

• #706 Qwen2.5-0.5B (42.4)
• #707 gemma-3-1b-it (42.4)
• #708 GPT-4o (Nov 2024) (42.3)
• #710 claude-2.0 (42.2)
• #711 qwen2.5-72b-instruct (42.2)
• #712 granite-3.1-1b-a400m-base (42.1)

More from OpenAI

• GPT-6 Astra (max) (#2, 64.0)
• GPT-6.1 Sol (max) (#5, 60.6)
• GPT-5.6 Sol (max) (#6, 60.1)
• GPT-6 Sol (max) (#7, 60.0)
• GPT-5.5 (xhigh) (#11, 58.0)
• GPT-5.6 Terra (max) (#12, 57.8)

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