Claude Opus 4.8 vs GLM 5
Head to head on 20 shared benchmarks, with price, context window, and release dates.
Benchmark scores
51evals · sort by any column, ⤢ to expand fullscreen
| Model | ||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 Anthropic | 66.7% | 1835elo | 80.8 | 47.2% | 92.0% | 48.7% | 62.2% | 80.1% | 79.3% | 78.3% | 67.4% | 81.4% | 84.3% | 89.7% | 91.8% | 53.5% | 75.6% | 58.3% | 82.7% | 94.4% | 15.5% | 80.4% | 14.5% | 67.0% | - | 1281elo | 40.0% | 53.9% | - | 13.4% | 22.5% | 1890elo | 56.9% | - | - | - | 10.4% | 53.2% | 85.8% | 69.9% | 83.4% | 69.0% | 54.8% | - | - | - | 69.2% | - | 82.7% | 60.9% | 70.9% | 63.4% |
| GLM 5 Zai | 62.9% | 1598elo | 70.9 | 16.4% | 66.6% | 7.6% | 55.2% | 71.2% | 73.6% | 67.9% | 55.3% | 77.5% | 83.5% | 69.1% | 65.2% | 38.3% | 70.0% | 39.4% | 23.4% | 97.4% | - | - | - | - | 7.9% | - | - | - | 24.7% | - | - | - | - | 97.9 | 82.7% | 48395 | - | - | - | - | - | - | - | 73.3 | 69.7% | 72.8% | - | 61.12 | - | - | - | 56.4% |
2 / 2 models
| Attribute | Claude Opus 4.8 Anthropic | GLM 5 Zai |
|---|---|---|
| Description | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) is an AI model from Anthropic. | GLM-5 is an AI model from Zai, released with open weights. |
| Family | Claude | Glm |
| Params | - | - |
| Open weights | - | open |
| License | - | mit |
| Released | 28 May 2026 | 11 Feb 2026 |
| Context | 1,000,000 | 204,800 |
| Input $/1M | $5.00 | $1.00 |
| Output $/1M | $25.00 | $3.20 |
| Cache read $/1M | $0.500 | $0.120 |
| Cache write $/1M | $6.250 | - |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | text, image, file | text |
| Providers | - | - |
| Publisher | Anthropic | Zai |
| Reported scores | GPQA Diamond66.6% (AA) Humanity's Last Exam (HLE)7.6% (AA) IFBench55.2% (AA) SciCode38.3% (AA) τ²-bench (Tau²-bench)97.4% (AA) |
FAQ
- Is Claude Opus 4.8 or GLM 5 better?
- Across the 20 benchmarks both models report on Sophon, Claude Opus 4.8 leads on 19 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do Claude Opus 4.8 and GLM 5 compare on GPQA Diamond?
- Claude Opus 4.8 scores 92.0% and GLM 5 scores 66.6% on GPQA Diamond.
- Which is cheaper, Claude Opus 4.8 or GLM 5?
- GLM 5 is cheaper at $3.20 per million output tokens against $25.00 for Claude Opus 4.8 - about 7.8x.
- When were Claude Opus 4.8 and GLM 5 released?
- Claude Opus 4.8 was released 28 May 2026 by Anthropic. GLM 5 was released 11 Feb 2026 by Zai.
Comparing something else? Build your own side-by-side.