GPT-3.5-turbo
| Released | 2023-03-01 |
|---|---|
| Price per 1M | $0.50 in · $1.50 out |
| Overall score | 25.6 · rank 234 |
| Context window | 16,385 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 25.6 | 234 | 9 |
| Overall: Coding | 24.4 | 234 | 4 |
| Overall: Reasoning | 30.0 | 230 | 6 |
| Overall: Agentic work | 23.3 | 235 | 4 |
| Agents | 21.6 | 189 | 1 |
| Reasoning | 30.1 | 226 | 3 |
| Math | 29.9 | 191 | 3 |
| General | 22.4 | 188 | 2 |
| Value vs price | −21.4 | 194 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 25.5 ±3.5 | 9 |
| High | 29.2 ±7.2 | 1 |
Evidence
Agents 21.6 ±2.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| METR 50% Time Horizon | $1 | METR | 2026-11-11 |
| METR task suite | 21.5% | Epoch AI | 2026-11-11 |
Reasoning 30.1 ±6.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleBench | 8.0% | SimpleBench | 2026-11-11 |
| Mystery Game Puzzles | 3.0% | Epoch AI | 2026-08-27 |
| GPQA Diamond | 28.0% | Epoch AI | 2025-01-27 |
| GPQA Diamond (Vals run) | 30.6% | Vals AI | 2026-09-01 |
Math 29.9 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 0.0% | Epoch AI | 2026-08-27 |
| MATH Level 5 | 15.9% | Epoch AI | 2025-01-27 |
| OTIS Mock AIME 2024-2025 | 2.2% | Epoch AI | 2026-08-07 |
General 22.4 ±2.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| EQ-Bench Creative Writing v3 | 450 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,226 | LMArena | 2026-11-09 |
Names matched to this model
gpt-3-5-turbo, gpt-3-5-turbo-0125, gpt-3-5-turbo-0301, gpt-3-5-turbo-0613, gpt-3-5-turbo-1106, gpt-3-5-turbo-16k-0613, gpt-3-5-turbo-instruct