GLM 5 vs GPT-5
Head to head on 15 shared benchmarks, with price, context window, and release dates.
Benchmark scores
77evals · sort by any column, ⤢ to expand fullscreen
| Model | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5 OpenAI | 95.0% | 61.1% | 1626elo | 72.8 | 32.4% | 86.2% | 25.3% | 73.1% | 83.4% | 42.9% | 74.4% | 73.4% | 32.6% | 20.1% | 84.8% | 46.7% | 91.1% | 88.0% | 94.6% | 0.0% | 0.15 | 0.0% | 68.1% | 4.58 | - | 57.7% | 80.0% | 80.0% | 91.7% | - | 0.0% | 88.9% | 83.3% | 100.0% | - | 48.9% | - | 58.2% | - | - | - | - | - | - | - | 84.6% | 37.5% | 0.52 | 1.62 | 100.0% | 99.4% | - | 0.0% | 92.7% | 92.7% | 49.6% | 83.7% | 93.3% | 10.0% | 87.1% | 0.0% | 65.5% | 60.0% | 0.26 | 0.0% | 18.0% | 43.7% | - | 74.9% | - | 2.34 | - | 87.5% | 0.86 | 54.8% | 90.0% | 90.0% | 61.8% |
| GLM 5 Zai | 96.7% | 62.9% | 1601elo | 70.9 | 16.4% | 87.8% | 29.3% | 72.3% | 82.7% | 46.2% | 72.8% | 70.0% | 43.2% | 23.4% | 98.2% | - | - | - | - | - | - | - | - | - | 7.9% | - | - | - | - | 24.7% | - | - | - | - | 97.9 | - | 48395 | - | 71.2% | 73.6% | 67.9% | 55.3% | 77.5% | 83.5% | 69.1% | - | - | - | - | - | - | 65.2% | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | 73.3 | - | 69.7% | - | 61.12 | - | - | - | - | - | 61.2% |
2 / 2 models
| Attribute | GLM 5 Zai | GPT-5 OpenAI |
|---|---|---|
| Description | GLM-5 is an AI model from Zai, released with open weights. | OpenAI's August 2025 unified frontier model that auto-routes between a fast model and a deeper "thinking" variant. |
| Family | Glm | GPT 5 |
| Params | - | Undisclosed (closed) |
| Open weights | open | closed |
| License | mit | proprietary |
| Released | 11 Feb 2026 | 7 Aug 2025 |
| Context | 204,800 | 400,000 |
| Input $/1M | $1.00 | $1.25 |
| Output $/1M | $3.20 | $10.00 |
| Cache read $/1M | $0.200 | $0.125 |
| Cache write $/1M | - | - |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | text | text, image, file |
| Providers | - | openai |
| Publisher | Zai | OpenAI |
| Reported scores | GPQA Diamond87.8% Humanity's Last Exam (HLE)29.3% (AA) IFBench72.3% (AA) SciCode46.2% (AA) τ²-bench (Tau²-bench)98.2% (AA) |
FAQ
- Is GLM 5 or GPT-5 better?
- Across the 15 benchmarks both models report on Sophon, GLM 5 leads on 8 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do GLM 5 and GPT-5 compare on GPQA Diamond?
- GLM 5 scores 87.8% and GPT-5 scores 86.2% on GPQA Diamond.
- Which is cheaper, GLM 5 or GPT-5?
- GLM 5 is cheaper at $3.20 per million output tokens against $10.00 for GPT-5 - about 3.1x.
- When were GLM 5 and GPT-5 released?
- GLM 5 was released 11 Feb 2026 by Zai. GPT-5 was released 7 Aug 2025 by OpenAI.
Other head-to-heads
56GPT-4.1 Mini vs GPT-541 shared evalsGPT-5 vs GPT-5 Mini36 shared evalsClaude Sonnet 4.5 vs GPT-531 shared evalsGPT-5 vs GPT-5 Nano28 shared evalsGPT-4.1 vs GPT-528 shared evalsGLM 5 vs Kimi K2.527 shared evalsClaude 4 Sonnet vs GPT-525 shared evalsClaude Sonnet 4.5 vs GLM 524 shared evalsGemini 2.5 Pro vs GPT-524 shared evalsGLM 5 vs GPT-5.224 shared evalsClaude Opus 4.5 vs GLM 524 shared evalsClaude Opus 4.6 vs GLM 524 shared evalsDeepSeek V3.2 vs GLM 524 shared evalsGPT-5 vs GPT-5.223 shared evalsClaude Opus 4.5 vs GPT-523 shared evalsGLM 5 vs GPT-5 Mini22 shared evalsGLM 5 vs GPT-5.422 shared evalsGPT-4.1 Nano vs GPT-521 shared evalsGemini 3.1 Pro Preview vs GLM 521 shared evalsGLM 5 vs Grok 4.1 Fast21 shared evalsGPT-5 vs Grok 4.1 Fast20 shared evalsGLM 5 vs GPT-5.520 shared evalsClaude Opus 4.8 vs GLM 520 shared evalsClaude Sonnet 4.6 vs GLM 520 shared evalsGLM 5 vs GLM 5.120 shared evalsClaude Opus 4.7 vs GLM 520 shared evalsGLM 5 vs Qwen3.6 Plus20 shared evalsGemini 3.1 Pro Preview vs GPT-519 shared evalsGPT-5 vs GPT-5.419 shared evalsClaude Opus 4.6 vs GPT-519 shared evalsGPT-5 vs Kimi K2.519 shared evalsGPT-4o vs GPT-519 shared evalsDeepSeek V3.2 vs GPT-519 shared evalsGLM 5 vs GPT-5 Nano19 shared evalsClaude 4 Sonnet vs GLM 519 shared evalsGLM 5 vs gpt-oss-120b19 shared evalsGLM 4.7 vs GLM 519 shared evalsGPT-5 vs GPT-5.518 shared evalsClaude Fable 5 vs GLM 518 shared evalsGemini 2.5 Pro vs GLM 518 shared evalsClaude Opus 4.8 vs GPT-517 shared evalsClaude Opus 4.7 vs GPT-517 shared evalsGPT-5 vs gpt-oss-120b17 shared evalsGLM 4.7 vs GPT-517 shared evalsClaude Fable 5 vs GPT-516 shared evalsGPT-4o-mini vs GPT-516 shared evalsClaude Sonnet 4.6 vs GPT-516 shared evalsGLM 5.1 vs GPT-516 shared evalsGPT-5 vs Qwen3.6 Plus15 shared evalsGLM 5 vs GPT-4o15 shared evalsGLM 5 vs GPT-4.1 Mini12 shared evalsGPT-5 vs GPT-6 Astra12 shared evalsGLM 5 vs GPT-4.112 shared evalsGLM 5 vs GPT-4o-mini12 shared evalsGLM 5 vs GPT-4.1 Nano12 shared evalsGLM 5 vs GPT-6 Astra7 shared evals
Comparing something else? Build your own side-by-side.