Head to head
Gemini 3.1 Pro and GLM 5.3 split the 4 shared benchmarks.
Gemini 3.1 Pro and GLM 5.3 split the 4 shared benchmarks.
| Dimension | Gemini 3.1 Pro | GLM 5.3 |
|---|---|---|
| GPQA Diamond | 94.3% | 88.1% |
| HLE | 44.4% | 42% |
| MathArena Apex | 60.9% | — |
| Terminal-Bench 2.1 | — | 88.2% |
| Terminal-Bench 3.0 | — | 28.3% |
| Terminal-Bench 4.0 | — | 37.9% |
| DeepSWE v1.1 | — | 66.9% |
| ProgramBench | — | 19% |
| NL2Repo-Bench | — | 58% |
| CyberGym | — | 84.5% |
| ExploitGym | — | 15% |
| HLE (w/tools) | 51.4% | 62.5% |
| Automation-Bench | 35.4% | 48.8% |
| Agents' Last Exam | — | 28.5% |
| Blended price | $7.00 /1M | — |
| Full priceInput · Output · Cached input | $2.00 · $12.00 · $0.200 | — |
| Context window | 1,000K | — |
Adjust the monthly volume — every model recomputes instantly.
Estimates use list prices and ignore cached input, batch discounts, and off-peak rates.