Compare models. Find the differences.
Add, remove, or change models in the table.
Benchmark snapshot
2 benchmarks in common.
4 models selected. 2 benchmarks in common.
Reported scores; test settings may differ.
| Benchmark | OpenAI | MiniMax | Anthropic | Google |
|---|---|---|---|---|
| Arena ELOHuman preference | 1,352 | 1,344 | 1,374 | 1,360 |
| GPQA DiamondScientific knowledge | Not in our dataset | Not in our dataset | 65.0% | 60.1% |
| HLEAcademic reasoning | 14.9% | Not in our dataset | 4.1% | Not in our dataset |
| MMLU ProMulti-task understanding | 81.0% | Not in our dataset | Not in our dataset | 77.6% |
| SimpleBenchCommonsense reasoning | 22.1% | 25.0% | 41.4% | 18.9% |
| GSOGraduate science | Not in our dataset | Not in our dataset | 4.6% | Not in our dataset |
| AiderCode editing | Not in our dataset | Not in our dataset | 51.6% | 22.2% |
| LiveCodeBenchCompetitive coding | Not in our dataset | Not in our dataset | 36.4% | Not in our dataset |
| Terminal-BenchAgentic terminal | 18.7% | 30.0% | Not in our dataset | Not in our dataset |
| ARC-AGI-2Visual reasoning | Not in our dataset | Not in our dataset | Not in our dataset | 1.3% |
Pricing & context Published USD rates per 1M tokens
| Specification | GPT-OSS 120B Non-thinking | M2 Reasoning | Claude 3 Sonnet 3.5 (October 2024) | Gemini 2.0 Flash |
|---|---|---|---|---|
| Input | $0.03 | $0.255 | $3 | $0.1 |
| Output | $0.136 | $1.02 | $15 | $0.4 |
| Context window | 131K | 205K | 200K | 1.0M |
| Pricing details | Explore pricing → | Explore pricing → | Explore pricing → | Explore pricing → |
How to read this comparison
Each column keeps the exact model version you selected. Shared benchmarks are the intersection of their reported results; “all coverage” also shows where evidence is missing. Missing results never count as zero.
These are published benchmark scores, not a controlled head-to-head test. The available evidence does not establish matching evaluation settings, so we show no cross-model winner highlights or deltas. Composite quality scores are omitted because they can summarize different benchmark sets.
Scores and statistics are computed upstream. This page reads a fixed data snapshot; its date describes the snapshot, not the date of every measurement.