← All benchmarks

Agentic arena

From Wikiprompt, the free prompt encyclopedia

Community Elo leaderboard, aggregated daily from LMArena head-to-head battles. Overall arena first, then per-category breakdowns.

Last updated: 2026-10-13 · 52 models

RankModelOrganizationElo score
1Claude Opus 5.5 (Max)anthropic
2GPT 6.1 Sol (Max)openai
3GPT 6 Sol (Max)openai
4Gemini 4 Argon (High)google
5GPT 6 Astra (Max)openai
6Claude Fable 5.1 (Max)anthropic
7Claude Sonnet 5.5 (Max)anthropic
8Claude Fable 5 (High)anthropic
9Claude Opus 5 (Max)anthropic
10Claude Opus 4.8 (High)anthropic
11GPT 5.6 Sol (xHigh)openai
12Gemini 3.8 Flash (High)google
13GPT 5.5 (xHigh)openai
14Claude Sonnet 5 (High)anthropic
15Grok 4.7 (xHigh)xai
16Deepseek V4.1 Flash (Max)deepseek
17Muse Spark 1.3 (Max)meta
18MiMo V2.6 Proxiaomi
19GLM 5.2 (Max)zai
20Kimi K3 (Max)moonshot
21DeepSeek V4 Pro (High) (0813)deepseek
22GPT 6 Luna (Max)openai
23GPT 5.4 (High)openai
24Hy4 previewtencent
25MiMo V2.6 Flashxiaomi
26Qwen3.8 Maxalibaba
27GLM 5.3 (Max)zai
28GPT 5.5openai
29GPT 5.6 Terra (xHigh)openai
30Grok 4.6 (xHigh)xai
31Grok 4.5xai
32Gemini 3.7 Flash (High)google
33GPT 5.6 Luna (xHigh)openai
34Step 5 Previewstepfun
35GLM 5.3 Flashzai
36Qwen3.8 Flash Nextalibaba
37Gemini 3.1 Pro Previewgoogle
38Qwen 3.8 27Balibaba
39Gemini 3.6 Flash (High)google
40Muse Spark 1.1meta
41Qwen3.7 Maxalibaba
42Hy3tencent
43Qwen3.7 Plusalibaba
44Mistral Large 4mistral
45Muse Spark 1.2 (xHigh)meta
46Mimo V2.5 Proxiaomi
47Minimax M3minimax
48Nemotron 3 Ultranvidia
49Mistral Medium 3.5mistral
50Inklingthinky
51Inkling Smallthinky
52Solar Pro 4upstage

See also

Sources and methodology

Rankings above are aggregated from open community evaluations. Elo ratings, confidence intervals and vote counts come from LMArena (crowdsourced head-to-head model battles, published as an open dataset). Model pricing and context metadata come from the public OpenRouter API. Wikiprompt snapshots these sources daily and preserves the history; we run no proprietary evaluations of our own.

  1. LMArena leaderboard dataset (Hugging Face)
  2. LMArena leaderboard