VIBE (MiniMax)
Agent builds complete web, simulation, Android, iOS or backend apps from scratch. Agent verifiers check execution, interaction and visuals.
VIBE v1 is open on Hugging Face (December 2025). MiniMax then reported harder internal versions, VIBE-Pro with M2.5 and VIBE-V2 with M3, which have their own records.
- Made by
- MiniMax
- Released
- December 2025
- Kind
- Building whole projects
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Code
- Tasks
- Public, plus a private test set
- Strongest model tested
-
Gemini 3 Pro #55 on the capability index - Last in a launch post
- December 2025, dropped after it saturated
- Last model added
- December 2025
- Scores refreshed
- November 12th, 2026
Claude Opus 4.5 leads with 90.7% among models released by December 2025
Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in December 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
- Gemini 4 Carbon
- GPT-6 Astra
- Claude Opus 5.5
- and 16 more
- 1 Claude Opus 4.5 90.7%
- 2
MiniMax-M2.1 88.6% - 3 Claude Sonnet 4.5 85.2%
- 4 Gemini 3 Pro 82.4%
- 5 MiniMax-M2 67.5%
Source: Official VIBE (MiniMax) leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.5 | 90.7% | Nov 2025 | Official leaderboard | |
| 2 | MiniMax-M2.1 | 88.6% | Dec 2025 | Official leaderboard | |
| 3 | Claude Sonnet 4.5 | 85.2% | Sep 2025 | Official leaderboard | |
| 4 | Gemini 3 Pro | 82.4% | Nov 2025 | Official leaderboard | |
| 5 | MiniMax-M2 | 67.5% | Oct 2025 | Official leaderboard |
Labs report scores for 1 model in their cards. We plot every source in the charts below.
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official VIBE (MiniMax) leaderboard
Claude Sonnet 4.5 on the official leaderboard passed 85% in September 2025
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official VIBE (MiniMax) leaderboard and labs’ model cards
Labs headline it less often now, last in December 2025
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Dec 23, 2025 | MiniMax-M2.1 | 88.6 | VIBE (Average) |
One lab claim next to the leaderboard
Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 1 of them match, which usually means one side copied the other. Every benchmark.
| Model | Lab says | Board says | Gap |
|---|---|---|---|
| MiniMax-M2.1 | 88.6% VIBE (Average) | 88.6% Leaderboard | Same |
Versions
More in Coding
- SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
- LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests.
DeepSeek-V4-Pro 93.5% - SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
- DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
- SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases.
Seed2.1 Pro 59.8% - Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471