Vibeleaderboard
← Benchmark guide

Model results

DesignArena

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Evaluation groups

Open a group to see its exact protocol and scores. Different configurations remain separate.

No model rankings are available in this snapshot. Reported results remain available below.

Other reported results

These reports have no model ranking. Open a group for its evidence and the reason positions are withheld.

  • Claude Fable 5overall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 16404 battles; Bradley-Terry standard error 2.9146; configuration claude-fable-5; result date not supplied; source captured 2026-09-10

  • Claude Fable 5.1overall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 6115 battles; Bradley-Terry standard error 4.6436; configuration claude-fable-5-1; result date not supplied; source captured 2026-09-10

  • Claude Haiku 4.5overall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 35537 battles; Bradley-Terry standard error 2.0176; configuration claude-haiku-4-5; result date not supplied; source captured 2026-09-10

  • Claude Opus 4overall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 16668 battles; Bradley-Terry standard error 2.839; configuration claude-opus-4; result date not supplied; source captured 2026-09-10

  • Claude Opus 4.5overall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 35203 battles; Bradley-Terry standard error 2.048; configuration claude-opus-4-5; result date not supplied; source captured 2026-09-10

  • Claude Opus 4.6overall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 23804 battles; Bradley-Terry standard error 2.4566; configuration claude-opus-4-6-thinking; result date not supplied; source captured 2026-09-10

  • Claude Opus 4.6overall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 27384 battles; Bradley-Terry standard error 2.3136; configuration claude-opus-4-6; result date not supplied; source captured 2026-09-10

  • Claude Opus 4.8overall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 25893 battles; Bradley-Terry standard error 2.343; configuration claude-opus-4-8; result date not supplied; source captured 2026-09-10

  • Claude Opus 5overall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 12546 battles; Bradley-Terry standard error 3.3017; configuration claude-opus-5; result date not supplied; source captured 2026-09-10

  • Claude Sonnet 4overall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 16246 battles; Bradley-Terry standard error 2.8596; configuration claude-sonnet-4-thinking; result date not supplied; source captured 2026-09-10

  • Claude Sonnet 4overall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 17542 battles; Bradley-Terry standard error 2.7643; configuration claude-sonnet-4; result date not supplied; source captured 2026-09-10

  • Claude Sonnet 4.5overall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 44183 battles; Bradley-Terry standard error 1.8288; configuration claude-sonnet-4-5-thinking; result date not supplied; source captured 2026-09-10

  • Claude Sonnet 4.5overall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 45423 battles; Bradley-Terry standard error 1.8066; configuration claude-sonnet-4-5; result date not supplied; source captured 2026-09-10

  • Claude Sonnet 4.6overall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 26298 battles; Bradley-Terry standard error 2.3409; configuration claude-sonnet-4-6; result date not supplied; source captured 2026-09-10

  • Claude Sonnet 5overall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 17860 battles; Bradley-Terry standard error 2.7734; configuration claude-sonnet-5; result date not supplied; source captured 2026-09-10

  • Gemini 3.8 Flashoverall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 9217 battles; Bradley-Terry standard error 3.8131; configuration gemini-3.8-flash; result date not supplied; source captured 2026-09-10

  • GLM 5.2overall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 30272 battles; Bradley-Terry standard error 2.2302; configuration glm-5.2; result date not supplied; source captured 2026-09-10

  • GPT-5.6 Soloverall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 6907 battles; Bradley-Terry standard error 4.3813; configuration gpt-5.6-sol-xhigh; result date not supplied; source captured 2026-09-10

  • GPT-5.6 Soloverall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 20815 battles; Bradley-Terry standard error 2.6413; configuration gpt-5.6-sol; result date not supplied; source captured 2026-09-10

  • GPT-6 Astraoverall-frontend

    DesignArena · DesignArena (reviewed publisher results)

    Single-model result · Positions withheld

    Measurement date not reported

    Scope · Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; …

    Overall Frontend (Text-to-HTML); arenaType=models; category=allcategories; inputModality=text; Elo; 4616 battles; Bradley-Terry standard error 5.4004; configuration gpt-6-astra; result date not supplied; source captured 2026-09-10

DesignArena model results | VibeLeaderboard