Tool

AI model comparator

Pick three models, get the verdict use by use. No test to run, no prompt to write — the comparison is already calculated.

  1. 1Tick three modelsin the table below, or in any ranking on the site.
  2. 2Run the comparisonin one click. Nothing to install, nothing to create.
  3. 3Read the verdictuse by use: who wins, by how much, and how solid the measurement is.

An example, calculated today

Claude opus 4.6Anthropic vsGemini 3 proGoogle vsDeepseek V4.1 Flash 20260910 (max)DeepSeek

Claude opus 4.6 leads 2 uses · Deepseek V4.1 Flash 20260910 (max) leads 1 use · Gemini 3 pro comes first on none.

3 uses settled out of 5 comparable · 2 too close to settle · 8 uses out of scope

Use-by-use comparison
Use Claude opus 4.6Gemini 3 proDeepseek V4.1 Flash 20260910 (max) Winner
General purpose 96.5 #4 93.1 #10 92.7 #11 Claude opus 4.6caveat
Conversation 94.4 #271 92.5 #286 91.0 #304 too close
Code 59.2 #192 46.5 #283 69.4 #127 Deepseek V4.1 Flash 20260910 (max)
Cost / performance 96.5 #15 94.5 #20 92.7 #25 too close
Cloud agents 96.5 #3 93.1 #9 92.7 #10 Claude opus 4.6caveat

The comparison is recalculated on every ranking update. Pick your own models below.

Compare the models of your choice

Le Recul comparator

Who wins on what

Tick at least two models in the ranking table, then come back here.

This list shows only the top twenty of the general ranking. The remaining 1,800 models — including code, image, video, audio and open models — are compared the same way from the full ranking, where the comparator works identically in each of the 13 categories.

Top twenty models in the general ranking
# Model Vendor Score
01 Claude opus 5.5 (high) Anthropic 98.6 / 100
02 Claude opus 4.6 (high) Anthropic 97.5 / 100
03 Claude opus 4.7 (high) Anthropic 97.2 / 100
04 Claude opus 4.6 Anthropic 96.5 / 100
05 Claude opus 4.7 Anthropic 95.9 / 100
06 Claude Fable 5 High Anthropic 95.4 / 100
07 Claude opus 4.8 (high) Anthropic 93.6 / 100
08 Claude Fable 5 1 Max Anthropic 93.1 / 100
09 Claude sonnet 5.5 (xhigh) Anthropic 93.1 / 100
10 Gemini 3 pro Google 93.1 / 100
11 Deepseek V4.1 Flash 20260910 (max) DeepSeek 92.7 / 100
12 GPT 5.2 chat (20260210) OpenAI 92.7 / 100
13 GPT 5.4 (high) OpenAI 92.6 / 100
14 Grok 4.20 beta 1 xAI 92.6 / 100
15 Claude opus 4.5 (high, 32k, 20251101) Anthropic 92.4 / 100
16 Claude opus 4.8 Anthropic 92.4 / 100
17 Qwen3.7 Max Preview Alibaba 92.4 / 100
18 Claude sonnet 4.6 Anthropic 92.0 / 100
19 Grok 4.20 beta (reasoning, 0309) xAI 92.0 / 100
20 Grok 4.20 multi Agent beta (0309) xAI 91.8 / 100

Compare across all 1,800 models →

Our written comparisons

The tool calculates. Our written comparisons explain: context, limits, and what the figures do not say.

GPT-6.1 Terra, GPT-6.1 Sol or Claude Sonnet 5.5: the cheapest per token is not always the cheapest per task

Comparisons

GPT-6.1 Terra, GPT-6.1 Sol or Claude Sonnet 5.5: the cheapest per token is not always the cheapest per task

GPT-6.1 Terra, launched by OpenAI on 26 October 2026, costs $1 per million input tokens: half the price of GPT-6.1 Sol and Claude Sonnet 5.5, both listed at $2. But a model is paid by the task, not by the token. We compared all three, with GPT-6 Luna and Claude Opus 5.5 as reference points, using the detailed values of OpenAI's charts, its safety card, independent measurements from Artificial Analysis and Plotly, and early user feedback. The verdict changes with the use case, and above all with the effort level you set.

Claude Sonnet 5.5 vs Muse Wonder Full: level at 56 on paper, two very different machines in practice

Comparisons

Claude Sonnet 5.5 vs Muse Wonder Full: level at 56 on paper, two very different machines in practice

On the leading independent ranking, Anthropic's Claude Sonnet 5.5 and Meta's new Muse Wonder Full both score 56 points, and split the ten tests five wins apiece. But one is available from $20 a month, the other from $50, and not on the same terms for your code. We set the independent measurements, the first published trials and nearly a thousand user comments against each other: in practice, the two models no longer look alike at all.

Best AI for coding: Claude Opus 5.5 against GPT-6 Sol, released the same day hours apart

Comparisons

Best AI for coding: Claude Opus 5.5 against GPT-6 Sol, released the same day hours apart

On 22 September 2026 Anthropic released Claude Opus 5.5, and OpenAI answered the same day with GPT-6 Sol at half the price. Both are sold for writing code. No independent coding leaderboard has measured either of them: SWE-bench Verified stopped accepting commercial labs in November 2025, and the DeepSWE leaderboard does not contain them. We went through both announcements line by line, cross-checked the only independent measurement available, recalculated every bill, and read the pricing tables down to the thresholds. Three things come out of it that appear in neither announcement: the more expensive model at its default setting beats the cheaper one at maximum, the price gap collapses exactly where code needs it, and neither vendor compared itself to the other.

See all comparisons →

Frequently asked questions

How many models can be compared at once?

Three. Beyond that the table becomes unreadable and the comparison loses its point: you do not choose between eight models, you choose between two or three finalists.

Where do the scores come from?

From cross-checked public sources, aggregated daily. Every score carries its evaluation status and the number of independent sources backing it.

What does “too close to call” mean?

That the gap between two models is smaller than the measurement uncertainty. Naming a winner in that case would be an arbitrary choice presented as a result: the comparator would rather say so.

Why do some cells say “not measured”?

Because the model does not appear in any public source for that use. Nothing is estimated or filled in: an empty cell is information, not an oversight.

Do I need an account?

No. The comparator is free, with no sign-up and no account. No personal data is requested.