All AI performance rankings
AI rankings for coding
Which AI is best at coding?
As of Nov 2026: #1
Gemini 4 Carbon, #2 Claude Opus 5.5, #3
Gemini 4 Neon. A coding performance ranking of 137 AI models across 19 evaluations, including Terminal-Bench 4.0 · Arena Coding · LiveBench Agentic Coding v1.
Last updated 2026-11-21 · AIB compiles and analyzes scores from many benchmarks to produce its own independent ranking.
This ranking combines the results of 19 tests for this use. Featured tests, recently updated tests and tests that many companies take part in count for more. Only models with scores on 2 or more tests are ranked. Scores are scaled so that the average model is 100; higher is better.
- 🥇GoogleGemini 4 Carbon4 tests counted134.3—1568—
- 🥈AnthropicClaude Opus 5.59 tests counted132.059.6%154865.3
- 🥉GoogleGemini 4 Neon3 tests counted130.4—1559—
- #4OpenAIGPT-6 Astra14 tests counted127.459.6%154857.3
- #5AnthropicClaude Fable 5.114 tests counted127.255.1%153366.1
- #6GoogleGemini 4 Argon9 tests counted125.057.1%1552—
- #7OpenAIGPT-6.1 Sol9 tests counted123.456.1%154556.8
- #8OpenAIGPT-6.1 Terra7 tests counted123.455.6%1541—
- #9MetaMuse Wonder5 tests counted123.052.0%1550—
- #10AnthropicClaude Sonnet 5.59 tests counted122.863.6%151739.3
- These models have scores on fewer than 2 tests, so they are left out of the ranking. They join it once they have 2 or more.
Recent ranking changes
Since tracking began on Nov 7, the #1, top 3 and top 10 models have not changed.
Frequently asked questions
- How is the ranking decided?
- Models are ordered by a combined score built from the results of 19 tests for this use. Featured tests, recently updated tests and tests that many companies take part in count for more, and a model with scores on only a few tests is pulled toward the average of models released around the same time. Only models with scores on 2 or more tests are ranked. Scores are scaled so that the average model is 100; higher is better. Pick one test above the table (Terminal-Bench 4.0, Arena Coding, LiveBench Agentic Coding v1) to reorder by that test.
- Where do the scores come from?
- We take the scores each test publishes, as they are. This ranking covers 19 tests and 137 AI models, and scores the AI maker reported itself are marked with a dotted underline.
- How often does the ranking change?
- We check test results every day and recalculate the ranking every hour. Results were last collected on 2026-11-21. Past changes are listed under Recent ranking changes.
- Which subscriptions include the top-ranked models?
- The plan comparison shows which models each ChatGPT, Claude, Gemini, Grok and other plan includes, with monthly prices and usage limits taken from the official pricing pages.
- What if a service is slow or down?
- The status page shows whether ChatGPT, Claude, Gemini, Grok and others are working right now and how many outages they had recently, based on their official status pages.