Benchmark Almanac

Vibe Code Bench 1-100 v1.1

GPT-6.2 Astra 55.2% leads since November 2026
Not in model cards
Version 1.1

Agents extend a working web application across successive requests while preserving earlier features.

Vals revised the requests and workflow assertions across 50 scenarios. A second model reviews browser-agent failure verdicts.

Made by
Vals AI
Released
November 2026
Kind
Building whole projects
Level
Expert
Scored
Graded by a model
Answers
Agent task
Tasks
Kept private
Measures
Capability
Language
English
In and out
Text, Code → Code, Actions
Interaction
Agentic
Environment
Terminal
Items from
Another benchmark
Run by
A host
In views
Agents
Strongest model tested
GPT-6.2 Astra #1 on the capability index
Last model added
November 2026
Scores refreshed
November 20th, 2026
11
Models scored on its own leaderboard

GPT-6.2 Astra leads with 55.2%

Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.

  1. 1 GPT-6.2 Astra 55.2%
  2. 2 Gemini 4 Carbon 49.7%
  3. 3 Gemini 4 Neon 42.3%
  4. 4 GPT-6.2 Sol 40.9%
  5. 5 Claude Opus 5.5 30.9%
  6. 6 GLM-5.3 29.8%
  7. 7 MiMo-V2.6 Pro 26.4%
  8. 8 Grok 4.7 26.4%
  9. 9 DeepSeek V4.1 Flash 1017 26.1%
  10. 10 MiMo-V2.6 Flash 24.5%
  11. 11 MiniMax-M3.1-Flash 19.8%

Source: Official Vibe Code Bench 1-100 v1.1 leaderboard

#ModelScore ±SettingDateSource
1 GPT-6.2 Astra 55.2% ±11.3 Nov 2026 Official leaderboard
2 Gemini 4 Carbon 49.7% ±9.6 Oct 2026 Official leaderboard
3 Gemini 4 Neon 42.3% ±9.8 Nov 2026 Official leaderboard
4 GPT-6.2 Sol 40.9% ±9.9 Nov 2026 Official leaderboard
5 Claude Opus 5.5 30.9% ±7 Sep 2026 Official leaderboard
6 GLM-5.3 29.8% ±8.5 Aug 2026 Official leaderboard
7 MiMo-V2.6 Pro 26.4% ±8.2 Sep 2026 Official leaderboard
8 Grok 4.7 26.4% ±8.3 Sep 2026 Official leaderboard
9 DeepSeek V4.1 Flash 1017 26.1% ±8.1 Oct 2026 Official leaderboard
10 MiMo-V2.6 Flash 24.5% ±8 Sep 2026 Official leaderboard
11 MiniMax-M3.1-Flash 19.8% ±7 Oct 2026 Official leaderboard

The best score, 55.2%, costs $46 a task

Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

Xiaomi Corp OpenAI Google DeepMind Cost frontier One model at each effort level
0% 20% 40% 60% $0.10 $1.00 $10 $100 $1,000 Cost per task, log scale GPT-6.2 Astra Gemini 4 Neon GPT-6.2 Sol MiMo-V2.6 Pro MiMo-V2.6 Flash 0% 20% 40% 60% $0.10 $1.00 $10 $100 $1,000 Cost per task, log scale GPT-6.2 Astra Gemini 4 Neon

Source: Official Vibe Code Bench 1-100 v1.1 leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-6.2 Astra 55.2% $46 368,427
Gemini 4 Carbon 49.7% $58 899,281
Gemini 4 Neon 42.3% $44 831,070
GPT-6.2 Sol 40.9% $13 420,131
Claude Opus 5.5 30.9% $115 2,923,431
GLM-5.3 29.8% $13 535,296
MiMo-V2.6 Pro 26.4% $1.32 385,760
Grok 4.7 26.4% $42 1,078,615
DeepSeek V4.1 Flash 1017 26.1% $2.68 859,225
MiMo-V2.6 Flash 24.5% $0.44 341,359
MiniMax-M3.1-Flash 19.8% $3.72 1,950,172

2 models have held number one on the official leaderboard since its release in November 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

Google DeepMind OpenAI
Own leaderboard 2 leaders

Source: Official Vibe Code Bench 1-100 v1.1 leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) GPT-6.2 Astra Gemini 4 Carbon Claude Opus 5.5 GLM-5.3 0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) GPT-6.2 Astra Claude Opus 5.5

Source: Official Vibe Code Bench 1-100 v1.1 leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

Versions

We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.

Anthropic Meta Google DeepMind OpenAI
Vibe Code Bench 1-100 v1.1 5 leaders

Source: Official leaderboards

More in Coding

All 523 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

Data audit

All 11 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access The tasks are private.
  • Pass Confidence Checked against a primary source.
Scores 5 pass
  • Pass Independent runs Scores from the official leaderboard (11 entries).
  • Pass Models scored 11 models we track.
  • Pass Newest score The newest is from November 2026, for Gemini 4 Neon.
  • Pass Frontier models 3 of the top 10 have a score, led by GPT-6.2 Astra (#1).
  • Pass Headroom The best is 55.2%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on vals.ai: 11 rows for models we track at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check