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 | Meta | Google | Anthropic | OpenAI |
|---|---|---|---|---|
| Arena ELOHuman preference | 1,327 | 1,365 | 1,325 | 1,337 |
| LiveBench 1.0General reasoning | 59.5% | 49.2% | Not in our dataset | Not in our dataset |
| GPQA DiamondScientific knowledge | 69.8% | 42.4% | Not in our dataset | 60.0% |
| HLEAcademic reasoning | 5.7% | Not in our dataset | Not in our dataset | Not in our dataset |
| MMLU ProMulti-task understanding | 80.5% | 67.5% | Not in our dataset | Not in our dataset |
| SimpleBenchCommonsense reasoning | 27.7% | Not in our dataset | Not in our dataset | 18.1% |
| AIME 2025Mathematics | 15.9% | 24.0% | Not in our dataset | Not in our dataset |
| AiderCode editing | 15.6% | 4.9% | 28.0% | 32.9% |
| LiveCodeBenchCompetitive coding | 37.2% | 29.7% | Not in our dataset | Not in our dataset |
| ARC-AGI-2Visual reasoning | 0.0% | Not in our dataset | Not in our dataset | 0.8% |
Pricing & context Published USD rates per 1M tokens
| Specification | Llama 4 Maverick Default (Non-thinking) | Gemma 3 27B IT Non-thinking | Claude 3.5 Haiku Non-thinking | o1 Mini Thinking |
|---|---|---|---|---|
| Input | $0.188 | $0.08 | $1 | $1.1 |
| Output | $0.652 | $0.35 | $5 | $4.4 |
| Context window | 524K | 131K | 200K | 128K |
| 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.