benchmark evidence
BenchLM Coding
BenchLM composite coding score (0-100).
winner on BenchLM Coding
OpenAI: GPT-5.486.4
direct benchmark result, not a broad vertical composite | source row dated 2026-07-09
scored on 2026-07-09
latest mapped results | top 20
| # | Model | Score | Evidence | Tested |
|---|---|---|---|---|
| 1 | OpenAI: GPT-5.4 | 86.4 | model-only aggregator | 2026-07-09 |
| 2 | Anthropic: Claude Opus 4.6 | 82.4 | model-only aggregator | 2026-07-09 |
| 3 | DeepSeek: DeepSeek V4 Flash | 81.8 | model-only aggregator | 2026-07-09 |
| 4 | Anthropic: Claude Sonnet 4.6 | 75.7 | model-only aggregator | 2026-07-09 |
| 5 | Anthropic: Claude Sonnet 4.5 | 74.4 | model-only aggregator | 2026-07-09 |
| 6 | OpenAI: GPT-5.2 | 73.7 | model-only aggregator | 2026-07-09 |
| 7 | Anthropic: Claude Opus 4.5 | 73.0 | model-only aggregator | 2026-07-09 |
| 8 | OpenAI: GPT-5.5 | 72.5 | model-only aggregator | 2026-07-09 |
| 9 | Z.ai: GLM 5 | 71.9 | model-only aggregator | 2026-07-09 |
| 10 | OpenAI: GPT-5.1 | 69.5 | model-only aggregator | 2026-07-09 |
| 11 | OpenAI: GPT-5.4 Mini | 68.5 | model-only aggregator | 2026-07-09 |
| 12 | DeepSeek: DeepSeek V4 Pro | 68.1 | model-only aggregator | 2026-07-09 |
| 13 | OpenAI: GPT-4.1 | 61.5 | model-only aggregator | 2026-07-09 |
| 14 | Google: Gemini 2.5 Pro | 46.1 | model-only aggregator | 2026-07-09 |
what this result means
BenchLM composite coding score (0-100).
This benchmark contributes direct public evidence. Read its scope before generalizing the result.
A win here is a win on BenchLM Coding. Broad task pages require independent corroboration before naming a general winner.
source record
category: coding
metric: score
matched models: 14
latest source date: 2026-07-09
direction: higher is better