AlgoTune leaderboard
As of 6 Nov 2026, the top score on AlgoTune is 2.0, shared by GPT-5.2 and Gemini 3.1 Pro, ahead of GPT-5.4 at 1.9, across 18 model configurations with a published result (AlgoTune, result dated 11 Dec 2025). The model optimises functions and is scored on speed-up versus the reference. AlgoTune is shown for reference only and does not count toward the BenchLeader Index.
Key facts (as of 6 Nov 2026)
- GPT-5.2 and Gemini 3.1 Pro share the top AlgoTune score at 2.0 (AlgoTune, 6 Nov 2026).
- AlgoTune: Speeding up numeric code beyond reference implementations (AlgoTune).
- 18 model configurations have a published AlgoTune result on BenchLeader (BenchLeader, 6 Nov 2026).
- AlgoTune does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).
Speeding up numeric code beyond reference implementations.
- Published by
- AlgoTunedata via Epoch AI Benchmarking Hub
- Category
- Coding
- Index weight
- Reference only
- Models
- 18
- Data as of
- 6 Nov 2026
CC BY 4.0 — Epoch AI, ‘AI Benchmarking Hub’, epoch.ai/benchmarks. Mirrored boards credit their original publishers.
What the test looks like
The model optimises functions and is scored on speed-up versus the reference.
How it is scored
Speed-up score, as published by AlgoTune.
What to keep in mind
A speed-up multiple, not a percent.
- 1GPT-5.2 (medium)2.0
- 2Gemini 3.1 Pro2.0
- 3GPT-5.4 (high)1.9
- 4Gemini 3 Pro1.8
- 5Claude Opus 4.51.8
- 6o4-mini (high)1.7
- 7DeepSeek R11.7
- 8GPT-5 (high)1.7
- 9Claude Sonnet 4.51.5
- 10GLM-4.5 (thinking)1.5
- 11Gemini 2.5 Pro1.5
- 12Claude Opus 4.6 (high)1.5
- 13Qwen3 Coder 480B1.4
- 14gpt-oss-120b (high)1.4
- 15GPT-5 mini (high)1.4
| # | ||||
|---|---|---|---|---|
| 1 |  GPT-5.2medium | 2.0 | 56.2 | 2025-12-11 |
| 2 |  Gemini 3.1 Pro | 2.0 | 60.5 | 2026-02-19 |
| 3 | GPT-5.4high | 1.9 | 58.8 | 2026-03-05 |
| 4 | Gemini 3 Pro | 1.8 | 60.2 | 2025-11-18 |
| 5 |  Claude Opus 4.5 | 1.8 | 57.9 | 2025-11-24 |
| 6 | o4-minihigh | 1.7 | 50.3 | 2025-04-16 |
| 7 |  DeepSeek R1open ↗ | 1.7 | 47.3 | 2025-01-20 |
| 8 | GPT-5high | 1.7 | 57.9 | 2025-08-07 |
| 9 | Claude Sonnet 4.5 | 1.5 | 53.7 | 2025-09-29 |
| 10 |  GLM-4.5thinkingopen ↗ | 1.5 | – | 2025-08-05 |
| 11 | Gemini 2.5 Pro | 1.5 | 54.5 | 2025-06-17 |
| 12 | Claude Opus 4.6high | 1.5 | 62.6 | 2026-02-05 |
| 13 |  Qwen3 Coder 480Bopen ↗ | 1.4 | 48.8 | 2025-07-31 |
| 14 | gpt-oss-120bhighopen ↗ | 1.4 | 48.9 | 2025-08-05 |
| 15 | GPT-5 minihigh | 1.4 | 54.6 | 2025-08-07 |
| 16 | Claude Opus 4.1 | 1.3 | 51.4 | 2025-08-05 |
| 17 | Claude Opus 4 | 1.3 | 52.6 | 2025-05-22 |
| 18 | GPT-5 Promedium | 1.3 | – | 2025-10-07 |
More coding benchmarks · All LLM benchmarks
Related benchmarks
Top head-to-heads on AlgoTune
Cite as: BenchLeader, “AlgoTune leaderboard”, data as of 6 Nov 2026, https://www.benchleader.com/benchmarks/algotune.
AlgoTune: questions
- What does AlgoTune measure?
- The model optimises functions and is scored on speed-up versus the reference. Scores are reported in score; higher is better.
- What is the top score on AlgoTune?
- As of 6 Nov 2026, the highest score on AlgoTune is 2.0, shared by GPT-5.2 and Gemini 3.1 Pro, ahead of GPT-5.4 at 1.9. Scores come from AlgoTune and are re-read daily.
- Which AI model leads AlgoTune?
- GPT-5.2 and Gemini 3.1 Pro tie for first on AlgoTune at 2.0 as of 6 Nov 2026, ahead of GPT-5.4 at 1.9.
- How many models have AlgoTune results?
- 18 model configurations have a AlgoTune result on BenchLeader, all taken from AlgoTune via Epoch AI Benchmarking Hub.
- Who runs AlgoTune and how often is it updated?
- AlgoTune is published by AlgoTune. BenchLeader re-reads the published results once a day and records the date each result was published.
- Does AlgoTune count toward the BenchLeader Index?
- No. AlgoTune is shown for reference but left out of the composite index.