GPT-3.5 Turbo (Jan 2024): benchmark scores, price and ranking
GPT-3.5 Turbo (Jan 2024) from OpenAI ranks #741 of 743 LLMs on the LLMs Tiger aggregate benchmark score (38.5), based on 9 benchmark results captured up to 2026-10-13.
- Organisation
- OpenAI
- Type
- Frontier model
- Open weights
- No
- Released
- 2024-01-25 (source: epoch)
- Cheapest API price
- $0.500 in / $1.50 out per million tokens (via azure, observed 2026-10-13T19:47Z)
- Aggregate rank
- #741 of 743 (score 38.5)
Relative to other models, GPT-3.5 Turbo (Jan 2024) is strongest on Epoch ECI (#146 of 204) and weakest on FrontierMath T1-3 (#68 of 68).
Across the 9 benchmarks where at least ten models are scored, GPT-3.5 Turbo (Jan 2024) is in the top 10% on 0 and in the top half on 0.
Its cheapest listed input price, $0.500 per million tokens, is lower than that of 48% of the 427 models with a listed price.
GPT-3.5 Turbo (Jan 2024) benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Epoch ECI | 116 | #146 of 204 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Chess Puzzles | 0.0% | #106 of 122 | Epoch AI Benchmarking Hub | 2026-10-13 |
| LMCA | 9.7% | #96 of 108 | Epoch AI Benchmarking Hub | 2026-10-13 |
| OTIS Mock AIME | 2.2% | #172 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| DTBench | 48.5% | #136 of 146 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GPQA Diamond | 27.2% | #258 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| WeirdML | 3.5% | #107 of 109 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Mystery Games | 3.0% | #58 of 59 | Epoch AI Benchmarking Hub | 2026-10-13 |
| FrontierMath T1-3 | 0.0% | #68 of 68 | Epoch AI Benchmarking Hub | 2026-10-13 |
About GPT-3.5 Turbo (Jan 2024)
GPT-3.5 Turbo (Jan 2024) is a frontier model from OpenAI. It was released on 2024-01-25, according to Epoch AI. The cheapest API listing we track charges $0.500 per million input tokens and $1.50 per million output tokens, through azure. We hold 9 benchmark results for it across 3 areas, and none is in the top tenth of its board.
Where GPT-3.5 Turbo (Jan 2024) stands
On our aggregate score, GPT-3.5 Turbo (Jan 2024) is #741 of 743 ranked models, in the lower half. Its score is 38.5; the scale is centred on 50, so it sits 11.5 points below the typical model. That beats 0% of the ranked field. Among the 88 ranked OpenAI models it is #87. The next one up is GPT-4.1 nano at 38.7. The next one down is gpt-4o-mini-2024-07-18 at 38.3.
GPT-3.5 Turbo (Jan 2024), benchmark by benchmark
GPT-3.5 Turbo (Jan 2024) lands below the middle on Epoch ECI: 116, #146 of 204, with 71% of the field scoring higher. Qwen 3.8 Max leads at 156; the closest result above is Gemma 3 4B at 116. It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so GPT-3.5 Turbo (Jan 2024) is 12 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Chess Puzzles is a weak spot. GPT-3.5 Turbo (Jan 2024) scores 0.0%, #106 of 122, behind 86% of the models measured. The leader, GPT-6 Astra (max), reaches 72.0%. It covers chess tactics puzzles. The board median is 12.5%, so GPT-3.5 Turbo (Jan 2024) is 12.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
LMCA is a weak spot. GPT-3.5 Turbo (Jan 2024) scores 9.7%, #96 of 108, behind 88% of the models measured. The leader, Claude Opus 5.5 (max), reaches 68.2%. It covers language-model capability assessment. The board median is 29.2%, so GPT-3.5 Turbo (Jan 2024) is 19.6 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
OTIS Mock AIME is a weak spot. GPT-3.5 Turbo (Jan 2024) scores 2.2%, #172 of 189, behind 90% of the models measured. The leader, Claude Fable 5.1 (max), reaches 100.0%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so GPT-3.5 Turbo (Jan 2024) is 55.6 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
DTBench is a weak spot. GPT-3.5 Turbo (Jan 2024) scores 48.5%, #136 of 146, behind 92% of the models measured. The leader, Claude Opus 5.5 (max), reaches 98.9%. It covers dynamic tool-use benchmark. The board median is 68.8%, so GPT-3.5 Turbo (Jan 2024) is 20.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
GPQA Diamond is a weak spot. GPT-3.5 Turbo (Jan 2024) scores 27.2%, #258 of 275, behind 93% of the models measured. The leader, GPT-6 Astra (max), reaches 95.8%. It covers expert-level science questions. The board median is 71.7%, so GPT-3.5 Turbo (Jan 2024) is 44.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
WeirdML is a weak spot. GPT-3.5 Turbo (Jan 2024) scores 3.5%, #107 of 109, behind 97% 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-3.5 Turbo (Jan 2024) is 37.7 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Mystery Games is a weak spot. GPT-3.5 Turbo (Jan 2024) scores 3.0%, #58 of 59, behind 97% of the models measured. The leader, GPT-6 Astra (max), reaches 84.0%. It covers deductive reasoning puzzles. The board median is 23.0%, so GPT-3.5 Turbo (Jan 2024) is 20.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
FrontierMath T1-3 is a weak spot. GPT-3.5 Turbo (Jan 2024) scores 0.0%, #68 of 68, behind 99% 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-3.5 Turbo (Jan 2024) is 55.6 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Reasoning, maths and science: weak, ahead of 5% of the field on average across 3 benchmarks. Its best board here is OTIS Mock AIME (#172 of 189) and its weakest is FrontierMath T1-3 (#68 of 68). General knowledge and chat: weak, ahead of 11% of the field on average across 5 benchmarks. Its best board here is Epoch ECI (#146 of 204) and its weakest is Mystery Games (#58 of 59).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so GPT-3.5 Turbo (Jan 2024) costs about the same as 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).
Release history
The OpenAI model released before it was GPT-4 Turbo Preview (Nov 2023) on 2023-11-06, which scores 46.9. The next one was GPT-4 (0125) on 2024-01-25, at 49.4.
Reading these numbers
The 9 scores on this page come from 1 source: Epoch AI Benchmarking Hub (9). No official leaderboard supplied any of them, so treat them as third-party measurements.
Models ranked nearby
- #738 Meta-Llama-3-8B-Instruct (39.4)
- #739 gemma-3-12b-it (39.1)
- #740 GPT-4.1 nano (38.7)
- #742 gpt-4o-mini-2024-07-18 (38.3)
- #743 Llama-3.1-8B-Instruct (36.7)
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