OpenAIGPT 4 0613
GPT 4 0613 is an OpenAI proprietary model, released 13 Jun 2023. Its best configuration ranks #676 of 784 on the BenchLeader Index at 39.7 ±6.0, in the lower half. The ± is the point: 287 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 human preference (42) and lowest in reasoning (31). At $37.50 per million tokens blended it is among the most expensive ranked models. Last measured 22 Oct 2026.
- Blended price
- $37.50/M
- $30.00 in · $60.00 out
- Output speed
- –
- First answer
- –
- Context
- 8k
- Full answer
- –
- Cost per run
- –
- Released
- 13 Jun 2023
- Overall index40
- Reasoning31
- Coding33
- Maths37
- Human preference42
Versions
OpenAI has shipped 13 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-5.6 | 9 Jul 2026 | – | – |
| GPT-5.5xhigh | 23 Apr 2026 | 66.1 | #35 |
| GPT-5.4xhigh | 5 Mar 2026 | 64.7 | #45 |
| GPT-5.2xhigh | 11 Dec 2025 | 60.7 | #106 |
| GPT-5.1high | 12 Nov 2025 | 57.7 | #171 |
| GPT-5high | 7 Aug 2025 | 57.9 | #166 |
| GPT-4.1 | 14 Apr 2025 | 48.3 | #426 |
| GPT-4.5 | 27 Feb 2025 | 49.7 | #387 |
| GPT 4 0125 | 25 Jan 2024 | – | – |
| GPT-4 1106 | 6 Nov 2023 | – | – |
| GPT 4 0613this page | 13 Jun 2023 | 39.7 | #676 |
| GPT-4 | 14 Mar 2023 | 42.4 | #595 |
| GPT-3.5 | – | – | – |
How its index has moved
10 Sept 2026 to 21 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 | 30.6%#269 | Epoch AI Benchmarking Hub | |
| Arena Hard Prompts | 1290#265 | Arena (LMArena) | |
| Mystery Game Puzzlesnot in index | 12.0%#103 | Epoch AI Benchmarking Hub | |
| LMCAnot in index | 17.1%#166 | Epoch AI Benchmarking Hub | |
| DTBenchnot in index | 62.7%#174 | Epoch AI Benchmarking Hub | |
| ForecastBenchnot in index | 61.5%#64 | ForecastBench | |
| BIG-Bench Hardnot in index | 75.1%#9 | Epoch AI Benchmarking Hub |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| WeirdML | 12.4%#147 | WeirdML | |
| Arena Coding | 1314#266 | Arena (LMArena) |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| OTIS Mock AIME | 1.1%#266 | Epoch AI Benchmarking Hub | |
| MATH Level 5 | 23.0%#75 | Epoch AI Benchmarking Hub | |
| Arena Maths | 1277#248 | Arena (LMArena) | |
| GSM8Knot in index | 90.0%#6 | Epoch AI Benchmarking Hub |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MMLUnot in index | 82.4%#13 | Epoch AI Benchmarking Hub | |
| TriviaQAnot in index | 84.8%#7 | Epoch AI Benchmarking Hub |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Instruction Followingnot in index | 1277#261 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1276#275 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1267#251 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1262#272 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1281#271 | 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 | $0.030 | – | – |
| Summarize a 30-page report | 12,000 / 600 | $0.396 | – | – |
| Code edit | 6,000 / 1,500 | $0.270 | – | – |
| Agentic coding session | 60,000 / 4,000 | $2.04 | – | – |
| Structured extraction | 2,000 / 200 | $0.072 | – | – |
See also
Questions people ask
- What are GPT 4 0613's benchmark scores?
- As of 26 Oct 2026, GPT 4 0613 scores 39.7 ±6.0 on the BenchLeader Index, strongest in human preference (42) and weakest in reasoning (31). That rests on 8 independent benchmark results, and every score on this page links to its publisher.
- How does GPT 4 0613 rank?
- GPT 4 0613 is #676 of 784 ranked configurations on 26 Oct 2026. 287 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 4 0613 cost per 1M tokens?
- As of 26 Oct 2026, GPT 4 0613 costs $30.00 per 1M input tokens and $60.00 per 1M output tokens, $37.50 blended (three input tokens per output token).
- When was GPT 4 0613 released?
- OpenAI released GPT 4 0613 on 13 Jun 2023.
Data as of 26 Oct 2026. Compare with another model.
Cite as: BenchLeader, “GPT 4 0613: benchmarks, pricing, speed and rank”, data as of 26 Oct 2026, https://www.benchleader.com/models/gpt-4-0613.