Coverage (30d)
18vs8
This Week
8vs3
Evidence
1 articlesRelationships
1Timeline
Claude Opus 4.72026-04-20
Anthropic released Claude Opus 4.7 with an updated tokenizer that increases token counts for the same input
Claude Opus 4.72026-04-20
Released Claude Opus 4.7 with 87.6% on SWE-Bench
Gemini 3 Pro2026-04-16
Achieved top score on METR time horizon benchmark, handling 90-minute software tasks
Gemini 3 Pro2026-02-20
Achieved state-of-the-art status on most benchmarks according to preliminary evaluations
Ecosystem
Claude Opus 4.7
deploysChain-of-Thought Prompting1 src
deploysConstitutional AI1 src
deploysRotary Position Embedding (RoPE)1 src
deploysTest-Time Compute Scaling1 src
deploysTransformer Self-Attention1 src
competes withGPT-5.31 src
Gemini 3 Pro
usesMMLU1 src
competes withGPT-4 Turbo1 src
competes withClaude 31 src
deploysChain-of-Thought Prompting1 src
deploysFlashAttention1 src
deploysGrouped-Query Attention (GQA)1 src
Benchmarks
mmlu pro
Claude Opus 4.7—
Gemini 3 Pro90.1
arena elo
Claude Opus 4.7—
Gemini 3 Pro1485
swe bench verified
Claude Opus 4.7—
Gemini 3 Pro80.6