gpt-4-turbo-2024-04-09: benchmark scores, price and ranking
gpt-4-turbo-2024-04-09 from OpenAI ranks #702 of 743 LLMs on the LLMs Tiger aggregate benchmark score (42.6), based on 9 benchmark results captured up to 2026-10-13.
- Organisation
- OpenAI
- Type
- Frontier model
- Open weights
- No
- Released
- 2024-04-09 (source: name)
- Context window
- 128,000 tokens
- Cheapest API price
- $10.00 in / $30.00 out per million tokens (via openai, observed 2026-10-13T19:47Z)
- Aggregate rank
- #702 of 743 (score 42.6)
Relative to other models, gpt-4-turbo-2024-04-09 is strongest on Aider Code Editing (#31 of 92) and weakest on FrontierMath T1-3 (#65 of 68).
Across the 9 benchmarks where at least ten models are scored, gpt-4-turbo-2024-04-09 is in the top 10% on 0 and in the top half on 1.
Its cheapest listed input price, $10.00 per million tokens, is lower than that of 4% of the 427 models with a listed price.
gpt-4-turbo-2024-04-09 benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Aider Code Editing | 63.9% | #31 of 92 | Aider Aider Code Editing leaderboard | 2026-10-13 |
| Chess Puzzles | 6.0% | #75 of 122 | Epoch AI Benchmarking Hub | 2026-10-13 |
| METR time horizon | 7 min | #22 of 31 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GPQA Diamond | 46.6% | #202 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Aider Refactoring | 34.1% | #9 of 12 | Aider Aider Refactoring leaderboard | 2026-10-13 |
| OTIS Mock AIME | 6.7% | #148 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SimpleBench | 25.1% | #50 of 61 | Epoch AI Benchmarking Hub | 2026-10-13 |
| WeirdML | 18.0% | #97 of 109 | Epoch AI Benchmarking Hub | 2026-10-13 |
| FrontierMath T1-3 | 0.7% | #65 of 68 | Epoch AI Benchmarking Hub | 2026-10-13 |
About gpt-4-turbo-2024-04-09
gpt-4-turbo-2024-04-09 is a frontier model from OpenAI. It was released on 2024-04-09, according to the model's own name. It accepts up to 128,000 tokens of input at once. The cheapest API listing we track charges $10.00 per million input tokens and $30.00 per million output tokens, through openai. We hold 9 benchmark results for it across 3 areas, and none is in the top tenth of its board.
Where gpt-4-turbo-2024-04-09 stands
On our aggregate score, gpt-4-turbo-2024-04-09 is #702 of 743 ranked models, in the lower half. Its score is 42.6; the scale is centred on 50, so it sits 7.4 points below the typical model. That beats 6% of the ranked field. Among the 88 ranked OpenAI models it is #82. The next one up is GPT-3.5 at 43.0. The next one down is GPT-4o (Nov 2024) at 42.3.
gpt-4-turbo-2024-04-09, benchmark by benchmark
Aider Code Editing puts gpt-4-turbo-2024-04-09 at 63.9%, #31 of 92. That beats 66% of the models tested, but 20.3 points short of Claude 3.5-Sonnet-20241022 (84.2%). The results either side are yi-lightning (65.4%) and nousresearch/hermes-3-llama-3.1-405b (63.9%). It covers Aider official benchmark. The board median is 55.6%, so gpt-4-turbo-2024-04-09 is 8.3 points above it. Source: Aider Aider Code Editing leaderboard, captured 2026-10-13.
gpt-4-turbo-2024-04-09 lands below the middle on Chess Puzzles: 6.0%, #75 of 122, with 61% of the field scoring higher. GPT-6 Astra (max) leads at 72.0%; the closest result above is GLM-4.7 at 6.0%. It covers chess tactics puzzles. The board median is 12.5%, so gpt-4-turbo-2024-04-09 is 6.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
gpt-4-turbo-2024-04-09 lands below the middle on METR time horizon: 7 min, #22 of 31, with 68% of the field scoring higher. Claude Mythos Preview (Early) leads at 1,045 min; the closest result above is GPT-4o (May 2024) at 9 min. It covers length of task (minutes) done at 50% success. The board median is 23 min, so gpt-4-turbo-2024-04-09 is 17 minutes below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
gpt-4-turbo-2024-04-09 lands below the middle on GPQA Diamond: 46.6%, #202 of 275, with 73% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is claude-3-opus-20240229 at 47.2%. It covers expert-level science questions. The board median is 71.7%, so gpt-4-turbo-2024-04-09 is 25.1 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
gpt-4-turbo-2024-04-09 lands below the middle on Aider Refactoring: 34.1%, #9 of 12, with 67% of the field scoring higher. Claude 3.5-Sonnet-20241022 leads at 92.1%; the closest result above is gpt-4o-2024-08-06 at 49.4%. It covers Aider official benchmark. The board median is 50.0%, so gpt-4-turbo-2024-04-09 is 15.9 points below it. Source: Aider Aider Refactoring leaderboard, captured 2026-10-13.
gpt-4-turbo-2024-04-09 lands below the middle on OTIS Mock AIME: 6.7%, #148 of 189, with 78% of the field scoring higher. Claude Fable 5.1 (max) leads at 100.0%; the closest result above is gemini-1.5-pro-001 at 6.8%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so gpt-4-turbo-2024-04-09 is 51.1 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
SimpleBench is a weak spot. gpt-4-turbo-2024-04-09 scores 25.1%, #50 of 61, behind 80% 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-4-turbo-2024-04-09 is 16.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
WeirdML is a weak spot. gpt-4-turbo-2024-04-09 scores 18.0%, #97 of 109, behind 88% of the models measured. The leader, GPT-6 Astra (max), reaches 93.3%. It covers unusual machine-learning tasks. The board median is 41.2%, so gpt-4-turbo-2024-04-09 is 23.2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
FrontierMath T1-3 is a weak spot. gpt-4-turbo-2024-04-09 scores 0.7%, #65 of 68, behind 94% 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-turbo-2024-04-09 is 54.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Reasoning, maths and science: weak, ahead of 18% of the field on average across 4 benchmarks. Its best board here is GPQA Diamond (#202 of 275) and its weakest is FrontierMath T1-3 (#65 of 68). General knowledge and chat: weak, ahead of 26% of the field on average across 4 benchmarks. Its best board here is Chess Puzzles (#75 of 122) and its weakest is WeirdML (#97 of 109).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so gpt-4-turbo-2024-04-09 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-opus-20240229 ($15.00) and GPT-4 (Mar 2023) ($30.00).
Release history
The OpenAI model released before it was GPT-4 Turbo Preview (January 2024) on 2024-01-25, which scores 46.9. The next one was GPT-4o on 2024-05-13, at 47.2.
Reading these numbers
The 9 scores on this page come from 3 sources: Epoch AI Benchmarking Hub (7), Aider Aider Code Editing leaderboard (1), Aider Aider Refactoring leaderboard (1). 2 of them come from an official leaderboard and 7 from datasets or third-party runs.
Models ranked nearby
- #699 Qwen2.5-Coder-0.5B-Instruct (42.6)
- #700 Llama-3.1-70B-Instruct (42.6)
- #701 Gemini 1.5 Flash (May 2024) (42.6)
- #703 ministral-8b-2410 (42.6)
- #704 Meta-Llama-3-70B-Instruct (42.5)
- #705 Qwen2-0.5B (42.4)
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