OpenAIGPT-3.5-turbo
GPT-3.5-turbo is an OpenAI proprietary model, released 18 Sept 2023. It is not yet ranked: 2 independent results so far, and the index needs at least five across two categories. At $0.750 per million tokens blended it is mid-priced. Output speed of 76 tokens per second puts it slower than most, with a first token in 0.6 s. It has been superseded by GPT 3.5 Turbo 0125, which is the version to compare against today. It has been measured at 2 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 13 Oct 2026.
- Blended price
- $0.750/M
- $0.500 in · $1.50 out
- Output speed
- 76 tok/s
- OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
- First answer
- 0.62 s
- Context
- 16k
- Full answer
- –
- Cost per run
- –
- Released
- 18 Sept 2023
- Knowledge27
Versions
OpenAI has shipped 4 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| GPT-4 Turbo | 9 Apr 2024 | 40.9 | #646 |
| GPT 3.5 Turbo 0125 | 25 Jan 2024 | 35.1 | #765 |
| GPT 3.5 Turbo 1106 | 6 Nov 2023 | 38.7 | #706 |
| GPT-3.5-turbohighthis page | 18 Sept 2023 | – | – |
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| highbest | – | – | 76 tok/s | 0.62 s | $0.0007 | Knowledge 27 |
| not stated | – | – | 76 tok/s | 0.62 s | $0.0007 | Composite 36 |
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | high | not stated | Source | Trend |
|---|---|---|---|---|
| GPQA Diamond (AA)not in indexeffort not stated | – | 29.7%#523 | Artificial Analysis | |
| GPQA Diamond (Vals)not in index | 30.6%#129 | – | Vals AI |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| METR Time Horizonsnot in index | 21.5%#38 | METR |
Knowledge
| Benchmark | high | Source | Trend |
|---|---|---|---|
| LegalBench | 64.4%#130 | Vals AI | |
| MedQA | 58.5%#83 | Vals AI |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 118.5#182 | Epoch AI Benchmarking Hub | |
| AA Intelligence Index v4.3.2 | 5.5#577 | Artificial Analysis |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Azure | 97 tok/s | 0.66 s | $3.00 | $4.00 | 16k | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0007 | – | 4.6 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0069 | – | 8.5 s |
| Code edit | 6,000 / 1,500 | $0.0053 | – | 20.4 s |
| Agentic coding session | 60,000 / 4,000 | $0.036 | – | 53.2 s |
| Structured extraction | 2,000 / 200 | $0.0013 | – | 3.2 s |
More from OpenAI
See also
Questions people ask
- Why does GPT-3.5-turbo have no BenchLeader Index score?
- The index needs at least five independent results across at least two categories; as of 25 Oct 2026 GPT-3.5-turbo has 2 that count. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
- How much does GPT-3.5-turbo cost per 1M tokens?
- As of 25 Oct 2026, GPT-3.5-turbo costs $0.500 per 1M input tokens and $1.50 per 1M output tokens, $0.750 blended (three input tokens per output token).
- When was GPT-3.5-turbo released?
- OpenAI released GPT-3.5-turbo on 18 Sept 2023. BenchLeader has results for it at 2 reasoning-effort settings.
Data as of 25 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “GPT-3.5-turbo: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/gpt-3-5-turbo.