OpenAIGPT 3.5 Turbo 1106
GPT 3.5 Turbo 1106 is an OpenAI proprietary model, released 6 Nov 2023. Its best configuration ranks #705 of 784 on the BenchLeader Index at 38.7 ±3.7, in the lower half. The ± is the point: 218 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in coding (37) and lowest in reasoning (28). At $1.25 per million tokens blended it is pricier than most ranked models. Last measured 22 Oct 2026.
- Blended price
- $1.25/M
- $1.00 in · $2.00 out
- Output speed
- –
- First answer
- –
- Context
- 16k
- Full answer
- –
- Cost per run
- –
- Released
- 6 Nov 2023
- Overall index39
- Reasoning28
- Coding37
- Maths34
- Human preference34
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 | #645 |
| GPT 3.5 Turbo 0125 | 25 Jan 2024 | 35.1 | #764 |
| GPT 3.5 Turbo 1106this page | 6 Nov 2023 | 38.7 | #705 |
| GPT-3.5-turbohigh | 18 Sept 2023 | – | – |
How its index has moved
10 Sept 2026 to 19 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
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 | not stated | Source | Trend |
|---|---|---|---|
| GPQA Diamond | 28.0%#275 | Epoch AI Benchmarking Hub | |
| Arena Hard Prompts | 1229#303 | Arena (LMArena) | |
| WinoGrandenot in index | 68.8%#48 | Epoch AI Benchmarking Hub | |
| ARC (AI2 Challenge)not in index | 87.4%#7 | Epoch AI Benchmarking Hub | |
| ANLInot in index | 58.1%#1 | Epoch AI Benchmarking Hub |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Coding | 1262#300 | Arena (LMArena) |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| BrowseCompnot in index | 0.6%#23 | OpenAI |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MATH Level 5 | 15.9%#82 | Epoch AI Benchmarking Hub | |
| Arena Maths | 1205#294 | Arena (LMArena) |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MMLUnot in index | 71.4%#49 | Epoch AI Benchmarking Hub | |
| TriviaQAnot in index | 85.8%#6 | Epoch AI Benchmarking Hub | |
| OpenBookQAnot in index | 86.0%#4 | Epoch AI Benchmarking Hub |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Instruction Followingnot in index | 1198#303 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1204#308 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1156#313 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1172#306 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1189#312 | Arena (LMArena) |
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 | $0.0010 | – | – |
| Summarize a 30-page report | 12,000 / 600 | $0.013 | – | – |
| Code edit | 6,000 / 1,500 | $0.0090 | – | – |
| Agentic coding session | 60,000 / 4,000 | $0.068 | – | – |
| Structured extraction | 2,000 / 200 | $0.0024 | – | – |
See also
Questions people ask
- What are GPT 3.5 Turbo 1106's benchmark scores?
- As of 26 Oct 2026, GPT 3.5 Turbo 1106 scores 38.7 ±3.7 on the BenchLeader Index, strongest in coding (37) and weakest in reasoning (28). That rests on 6 independent benchmark results, and every score on this page links to its publisher.
- How does GPT 3.5 Turbo 1106 rank?
- GPT 3.5 Turbo 1106 is #705 of 784 ranked configurations on 26 Oct 2026. 218 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does GPT 3.5 Turbo 1106 cost per 1M tokens?
- As of 26 Oct 2026, GPT 3.5 Turbo 1106 costs $1.00 per 1M input tokens and $2.00 per 1M output tokens, $1.25 blended (three input tokens per output token).
- When was GPT 3.5 Turbo 1106 released?
- OpenAI released GPT 3.5 Turbo 1106 on 6 Nov 2023.
Data as of 26 Oct 2026. Compare with another model.
Cite as: BenchLeader, “GPT 3.5 Turbo 1106: benchmarks, pricing, speed and rank”, data as of 26 Oct 2026, https://www.benchleader.com/models/gpt-3-5-turbo-1106.