Benchmark Almanac

DesignArena Blender

Claude Opus 5.5 1,413 leads since September 2026
Not in model cards

Agents build a 3D scene in Blender from a user prompt. Users compare the rendered scenes and vote for the better one.

One of 40 DesignArena boards. DesignArena ranks entries with Bradley-Terry ratings from user votes.

Kind
Building whole projects
Level
Everyday
Scored
Ranked by votes
Answers
Open-ended
Tasks
All public
Strongest model tested
GPT-6 Astra #3 on the capability index
Last model added
October 2026
Scores refreshed
November 12th, 2026
17
Entries on its own leaderboard, 12 models we track

Claude Opus 5.5 leads with 1,413

Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

17 entries. Scroll sideways for the rest. Bars start at 900.

  1. 1,413 Claude Opus 5.5
  2. 1,412 GPT-6 Astra
  3. 1,378 Gemini 4 Argon
  4. 1,371 Meshy 7.1
  5. 1,367 GPT-6.1 Sol
  6. 1,268 Claude Sonnet 5.5
  7. 1,192 Gemini 3.8 Flash
  8. 1,158 Muse Wonder
  9. 1,156 Kimi K3
  10. 1,154 Tripo H3.1
  11. 1,149 Grok 4.6
  12. 1,144 Hunyuan 3D v3.1 Pro
  13. 1,131 Muse Spark 1.3
  14. 1,124 Rodin Gen-2.5
  15. 1,107 Tripo P2
  16. 1,090 MiniMax-M3
  17. 997 Claude Sonnet 5

Bars start at 900.

  1. 1 Claude Opus 5.5 max 1,413
  2. 2 GPT-6 Astra xhigh, max 1,412
  3. 3 Gemini 4 Argon 1,378
  4. 4 Meshy 7.1 1,371
  5. 5 GPT-6.1 Sol max 1,367
  6. 6 Claude Sonnet 5.5 1,268
  7. 7 Gemini 3.8 Flash 1,192
  8. 8 Muse Wonder max 1,158
  9. 9 Kimi K3 1,156
  10. 10 Tripo H3.1 1,154
  11. 11 Grok 4.6 1,149
  12. 12 Hunyuan 3D v3.1 Pro 1,144
  13. 13 Muse Spark 1.3 xhigh 1,131
  14. 14 Rodin Gen-2.5 1,124
  15. 15 Tripo P2 1,107
  16. 16 MiniMax-M3 1,090
  17. 17 Claude Sonnet 5 997

Source: Official DesignArena Blender leaderboard

#EntryScoreSettingDateSource
1 Claude Opus 5.5 1,413 max Sep 2026 Official leaderboard
2 GPT-6 Astra 1,412 xhigh, max Sep 2026 Official leaderboard
3 Gemini 4 Argon 1,378 Sep 2026 Official leaderboard
4 Meshy 7.1 1,371 Official leaderboard
5 GPT-6.1 Sol 1,367 max Sep 2026 Official leaderboard
6 Claude Sonnet 5.5 1,268 Sep 2026 Official leaderboard
7 Gemini 3.8 Flash 1,192 Sep 2026 Official leaderboard
8 Muse Wonder 1,158 max Oct 2026 Official leaderboard
9 Kimi K3 1,156 Jul 2026 Official leaderboard
10 Tripo H3.1 1,154 Official leaderboard
11 Grok 4.6 1,149 Aug 2026 Official leaderboard
12 Hunyuan 3D v3.1 Pro 1,144 Official leaderboard
13 Muse Spark 1.3 1,131 xhigh Sep 2026 Official leaderboard
14 Rodin Gen-2.5 1,124 Official leaderboard
15 Tripo P2 1,107 Official leaderboard
16 MiniMax-M3 1,090 Jun 2026 Official leaderboard
17 Claude Sonnet 5 997 Jun 2026 Official leaderboard

More effort adds a median 49 elo

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
Claude Opus 5.5
high max
1,413
GPT-6 Astra
xhigh xhigh, max
1,412
GPT-6.1 Sol
max
1,367

Source: Official DesignArena Blender leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Opus 5.5 max 1,413
GPT-6 Astra xhigh, max 1,412
Gemini 4 Argon 1,378
GPT-6.1 Sol max 1,367
GPT-6 Astra xhigh 1,363
Claude Opus 5.5 high 1,290
GPT-6.1 Sol 1,274
Claude Sonnet 5.5 1,268
Claude Opus 5.5 1,256
Gemini 3.8 Flash 1,192
Muse Wonder max 1,158
Kimi K3 1,156
Grok 4.6 1,149
Muse Spark 1.3 xhigh 1,131
MiniMax-M3 1,090
Claude Sonnet 5 997

5 models have held number one on the official leaderboard since 2023

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

MiniMax Moonshot AI Google DeepMind OpenAI Anthropic
Own leaderboard 5 leaders
Claude Opus 5.5 1,413

Source: Official DesignArena Blender leaderboard

Scores over time

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

On the benchmark’s own leaderboard
1,000 1,200 1,400 2026 1,000 1,200 1,400 2026

Source: Official DesignArena Blender leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Coding

All 282 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