88Z.ai / RANKINGS
Gemini vs Claude: 2026 benchmark comparison
Compare Google Gemini and Anthropic Claude on overall, coding, vision and reasoning public scores.
Last collected by this site: 2026-11-15 06:40 (UTC+8, Asia/Shanghai). Source publication dates are in the table or the citations below.
Compare Google Gemini and Anthropic Claude on overall, coding, vision and reasoning public scores.
Gemini 4 Carbon
- Gemini 4 CarbonGoogle · overall 96.0
- Gemini 4 Hydrogen (High)Google · overall 90.4
- Gemini 4 ArgonGoogle · overall 89.0
- Gemini 3.7 Flash (High)Google · overall 85.9
- Gemini 3 FlashGoogle · overall 85.5
- Gemini 3 ProGoogle · overall 85.3
Claude Fable 5.1
- Claude Fable 5.1Anthropic · overall 96.5
- Claude Opus 5.5Anthropic · overall 95.0
- Claude Sonnet 5.5 (xHigh)Anthropic · overall 91.1
- Claude Fable 5.2Anthropic · overall 90.6
- Claude Opus 5 (Max)Anthropic · overall 90.2
- Claude Fable 5 (High)Anthropic · overall 89.2
Flagship comparison (best overall variant in each family)
| Metric | Gemini 4 Carbon | Claude Fable 5.1 |
|---|---|---|
| Overall | 96.0 | 96.5 |
| AA Intelligence Index | — | — |
| LMArena Text | — | — |
| LiveBench overall | 83.5 | 84.0 |
| Coding | 100 | 98.2 |
| Reasoning | 83.2 | 87.3 |
| Chinese (SuperCLUE or arena) | — | — |
| Vision arena | — | — |
This is not a declaration of an overall winner between labs. It places the same public scores side by side. See the methodology page for the full rules.
Sources
- LMArena Text Arena (style-controlled) — Official Arena leaderboard dataset, text_style_control / latest. Scores are Arena ratings (Bradley-Terry).
- LMArena WebDev Arena — Official webdev / latest snapshot, measuring front-end and web-app battles.
- LMArena Vision Arena (style-controlled) — Official vision_style_control / latest snapshot.
- LMArena Text-to-Image Arena — Official text_to_image / latest snapshot.
- LMArena Text-to-Video Arena — Official text_to_video / latest snapshot.
- LMArena Agent Arena — Official agent / latest aggregate scores.
- Artificial Analysis Intelligence Index — Intelligence Index, cost per task, time per task and first-token latency from the official public leaderboard page.
- LiveBench 2.0 — Official CSV results. Overall uses the published formula: Long Agentic ×2, Design ×1.5, Coding ×1.5, other suites ×1, then a weighted mean over suites that have a score.
- Aider Polyglot — Official polyglot_leaderboard.yml. The metric is pass_rate_2 on 225 cross-language exercises. Repeated submissions keep the best score.
- SWE-bench Verified (mini-SWE-agent) — Official leaderboards.json, Verified board, resolved % under the mini-SWE-agent protocol so models are compared in a similar scaffold. Scores from other agents are not mixed into the composite coding score.
- SuperCLUE Chinese general board — Total and section scores from the official monthly general-board spreadsheet.
FAQ
- Where do these scores come from?
- Every score comes from a public benchmark or official machine-readable file, with a source link and date. This site does not invent scores, and missing values are not treated as zero.
- Do you only compare a single winner from each lab?
- Each comparison lists leading flagship families from both labs and the same-source breakdowns. When a family has several variants (for example High or Max), the variant with the better overall score is used.
- Are site prices part of the benchmarks?
- No. Benchmark scores come from third-party public boards. CNY prices are this site’s catalogue reference rates (CNY 1 = 1,000 points) and are settled on actual usage. They are shown separately so billing is not confused with quality.