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.

Reported benchmark results for Qwen3 Max Qwen 3.8 Max, Claude Opus 4 4.7 Thinking, Claude Sonnet 5.5, Gemini 3.7 Flash
Benchmark
Qwen
Anthropic
Anthropic
Google
Arena ELOHuman preference1,4821,5011,4771,490
LiveBench 1.0General reasoning78.5%76.5%77.8%78.8%
GPQA DiamondScientific knowledgeNot in our dataset94.2%Not in our datasetNot in our dataset
HLEAcademic reasoningNot in our dataset46.9%46.1%Not in our dataset
SimpleBenchCommonsense reasoningNot in our dataset61.7%75.9%Not in our dataset
GSOGraduate scienceNot in our dataset44.1%Not in our datasetNot in our dataset
SWE-Bench VerifiedAgentic codingNot in our dataset87.6%Not in our datasetNot in our dataset
Terminal-BenchAgentic terminalNot in our dataset69.4%Not in our datasetNot in our dataset
ARC-AGI-2Visual reasoningNot in our dataset68.3%83.9%84.6%
Pricing & context Published USD rates per 1M tokens
SpecificationQwen3 Max Qwen 3.8 MaxClaude Opus 4 4.7 ThinkingClaude Sonnet 5.5Gemini 3.7 Flash
Input$0.78$5$2$0.75
Output$3.9$25$10$3.75
Context window262K1.0M1.0M1.0M
Pricing detailsExplore 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.