RankingLMArena Agent Arena

LMArena Agent Arena

Data updated 6 Oct 2026

Bucket
Supporting evidence
Unit
index
Direction
Higher is better
Version
2026-10-02
Display harness
LMArena Agent Arena · max
Board
https://arena.ai/leaderboard/agent

These rows are the aggregate Agent Arena IPS net improvement, in percentage points, with the board's session count. The text arena's Bradley-Terry rating is a different column. These rows stay out of the weighted Overall.

Compare published benchmark results with category weights →

Models

Results are ordered by score in the display harness, followed by models with no result. Other harnesses are listed separately below. Missing results remain unknown.

26–50 of 460 entries

ModelScoreEvidenceSource-recorded date
aya-vision-8bCohere———
C4Ai Aya Expanse 32BCohere———
C4Ai Aya Vision 32BCohere———
c4ai-command-r7b-arabic-02-2025Cohere———
chatglm-6bZ.ai———
chatglm2-6bZ.ai———
chatglm2-6b-32kZ.ai———
chatglm3-6bZ.ai———
chatglm3-6b-128kZ.ai———
chatglm3-6b-32kZ.ai———
Claude Fable 5Anthropic———
Claude Haiku 4.5Anthropic———
Claude Opus 4.5Anthropic———
Claude Opus 4.6Anthropic———
Claude Opus 4.7Anthropic———
Claude Opus 4.8Anthropic———
Claude Opus 5.5Anthropic———
Claude Sonnet 4.5Anthropic———
Claude Sonnet 4.6Anthropic———
Claude Sonnet 5Anthropic———
codegeex2-6bZ.ai———
codegeex4-all-9bZ.ai———
CodeGemma 7B ITGoogle———
Codestral 2508Mistral———
cogagent-9b-20241220Z.ai———

Other harnesses

These runs use other harnesses. Capability scoring matches configurations separately; model details identify which source records contribute.

ModelScoreHarnessEvidenceSource-recorded date
Claude Fable 5Anthropic8.21 LMArena Agent Arena · highofficial board2026-10-02
Claude Opus 4.8Anthropic6.64 LMArena Agent Arena · highofficial board2026-10-02
Claude Opus 5Anthropic8.67 LMArena Agent Arena · highofficial board2026-10-02
Claude Opus 5.5Anthropic13.82 LMArena Agent Arena · highofficial board2026-10-02
Claude Sonnet 5Anthropic4.4 LMArena Agent Arena · highofficial board2026-10-02
DeepSeek V4-Pro 0813DeepSeek1.19 LMArena Agent Arena · highofficial board2026-10-02
Gemini 3.1 ProGoogle-7.71 LMArena Agent Arena · unspecifiedofficial board2026-10-02
Gemini 3.6 FlashGoogle-7.68 LMArena Agent Arena · highofficial board2026-10-02
Gemini 3.7 FlashGoogle-1.49 LMArena Agent Arena · highofficial board2026-10-02
Gemini 3.8 FlashGoogle2.97 LMArena Agent Arena · highofficial board2026-10-02
Gemini 4 ArgonGoogle7.57 LMArena Agent Arena · highofficial board2026-10-02
GLM-5.3-FlashZ.ai-0.44 LMArena Agent Arena · unspecifiedofficial board2026-10-02
GPT-5.4OpenAI1.05 LMArena Agent Arena · highofficial board2026-10-02
GPT-5.5OpenAI1.04 LMArena Agent Arena · unspecifiedofficial board2026-10-02
GPT-5.5OpenAI4.15 LMArena Agent Arena · xhighofficial board2026-10-02
GPT-5.6 LunaOpenAI-1.17 LMArena Agent Arena · xhighofficial board2026-10-02
GPT-5.6 SolOpenAI6.45 LMArena Agent Arena · xhighofficial board2026-10-02
GPT-5.6 TerraOpenAI0.4 LMArena Agent Arena · xhighofficial board2026-10-02
Grok 4.6xAI1.28 LMArena Agent Arena · xhighofficial board2026-10-02
Grok 4.7xAI4.04 LMArena Agent Arena · xhighofficial board2026-10-02
Grok-4.5xAI1.21 LMArena Agent Arena · unspecifiedofficial board2026-10-02
Hy3Tencent-5.38 LMArena Agent Arena · unspecifiedofficial board2026-10-02
Hy4-previewTencent3.95 LMArena Agent Arena · unspecifiedofficial board2026-10-02
MiMo-V2.5-ProXiaomi-7.52 LMArena Agent Arena · unspecifiedofficial board2026-10-02
MiniMax-M3MiniMax-6.87 LMArena Agent Arena · unspecifiedofficial board2026-10-02
Mistral Medium 3.5Mistral-12.38 LMArena Agent Arena · unspecifiedofficial board2026-10-02
Muse Spark 1.1Meta-4.88 LMArena Agent Arena · unspecifiedofficial board2026-10-02
Muse Spark 1.2Meta-3.27 LMArena Agent Arena · xhighofficial board2026-10-02
Qwen 3.8-MaxQwen2.51 LMArena Agent Arena · unspecifiedofficial board2026-10-02
Qwen3.7-maxQwen-5.13 LMArena Agent Arena · unspecifiedofficial board2026-10-02
Qwen3.7-plusQwen-7.15 LMArena Agent Arena · unspecifiedofficial board2026-10-02
Qwen3.8-27BQwen-1.66 LMArena Agent Arena · unspecifiedofficial board2026-10-02
Qwen3.8-Flash-NextQwen-0.73 LMArena Agent Arena · unspecifiedofficial board2026-10-02
Solar Pro 4Upstage-15.9 LMArena Agent Arena · unspecifiedofficial board2026-10-02