HyperTask
MiniMax-M2.7 67.6% Only in system cards Agents build applications over long vibe coding sessions with about 100 feature or step requirements per task. Expert rubrics score the result over three trials.
In-house MiniMax evaluation. The tasks are not public.
- Level
- Expert Specialists with years of training, often over hours of work
- Scored
- Graded by a model A language model scores each response, usually against a rubric.
- Answers
- Agent task Many steps in a terminal, browser, desktop, app, game or robot.
MiniMax-M2.7 leads with 67.6%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 MiniMax-M2.7 67.6%
- 2 MiniMax-M2.5 59.4%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | MiniMax-M2.7 | 67.6% | May 2026 | Model card | |
| 2 | MiniMax-M2.5 | 59.4% | May 2026 | Model card |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
2 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 26 May 2026 | MiniMax-M2.7 technical report | 67.6 | HyperTask (Table 4) | Capabilities |
| 26 May 2026 | MiniMax-M2.5 technical report | 59.4 | HyperTask (Table 4) | Capabilities |
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%
- SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Opus 5.5 93.9%
- 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% - 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