Compare models. Find the differences.
Add, remove, or change models in the table.
Benchmark snapshot
0 benchmarks in common.
4 models selected. 0 benchmarks in common.
Reported scores; test settings may differ.
| Benchmark | Microsoft | OpenAI | Meta | Meta |
|---|---|---|---|---|
| Arena ELOHuman preference | 1,256 | 1,338 | 1,318 | Not in our dataset |
| LiveBench 1.0General reasoning | 41.6% | Not in our dataset | Not in our dataset | Not in our dataset |
| GPQA DiamondScientific knowledge | 56.1% | Not in our dataset | 50.5% | 49.0% |
| MMLU ProMulti-task understanding | Not in our dataset | Not in our dataset | 68.9% | 73.4% |
| SimpleBenchCommonsense reasoning | Not in our dataset | Not in our dataset | 19.9% | 23.0% |
| AIME 2025Mathematics | 17.3% | Not in our dataset | Not in our dataset | Not in our dataset |
| LiveCodeBenchCompetitive coding | 25.2% | Not in our dataset | Not in our dataset | Not in our dataset |
| Terminal-BenchAgentic terminal | Not in our dataset | 7.9% | Not in our dataset | Not in our dataset |
| ARC-AGI-2Visual reasoning | Not in our dataset | 2.6% | Not in our dataset | Not in our dataset |
Pricing & context Published USD rates per 1M tokens
| Specification | Phi-4 Non-Thinking | GPT-5 Nano Thinking (5.0) | Llama 3 70B 3.3 | Llama 3 405B 3.1 |
|---|---|---|---|---|
| Input | $0.07 | $0.05 | $0.1 | $4 |
| Output | $0.14 | $0.4 | $0.32 | $4 |
| Context window | 16K | 400K | 131K | 131K |
| 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.