BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases8

LMArena Longer Queries leaderboard

As of 5 Nov 2026, the top score on LMArena Longer Queries is 1542 by Gemini 4 Carbon (Google), ahead of Gemini 4 Argon at 1539, across 355 model configurations with a published result (Arena (LMArena), result dated 28 Oct 2026). Pairwise votes on prompts above a length threshold. LMArena Longer Queries is shown for reference only and does not count toward the BenchLeader Index.

Key facts (as of 5 Nov 2026)

  • Gemini 4 Carbon holds the top Arena Longer Queries score at 1542 (Arena (LMArena), 28 Oct 2026).
  • Gemini 4 Argon is second on Arena Longer Queries at 1539 (Arena (LMArena), 28 Oct 2026).
  • Arena Longer Queries: Text arena rating on long prompts (Arena (LMArena)).
  • 355 model configurations have a published Arena Longer Queries result on BenchLeader (BenchLeader, 5 Nov 2026).
  • Arena Longer Queries does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).

Text arena rating on long prompts.

Published by
Arena (LMArena)
Category
Human preference
Index weight
Reference only
Models
355
Data as of
5 Nov 2026

CC BY 4.0 — lmarena-ai/leaderboard-dataset on Hugging Face.

What the test looks like

Pairwise votes on prompts above a length threshold.

How it is scored

Bradley-Terry rating from pairwise votes, in Elo-like units, with style control.

What to keep in mind

Fewer votes than the overall board.

Top 15
  1. 1Gemini 4 Carbon (high)1542
  2. 2Gemini 4 Argon (high)1539
  3. 3Claude Opus 5.5 (high)1525
  4. 4Claude Fable 5 (high)1522
  5. 5Claude Opus 4.6 (high)1521
  6. 6Claude Opus 4.61516
  7. 7Claude Opus 4.7 (high)1515
  8. 8Claude Fable 5.1 (max)1512
  9. 9Gemini 3.8 Flash (high)1512
  10. 10Claude Opus 4.71508
  11. 11Muse Wonder (max)1505
  12. 12Claude Opus 5 (high)1504
  13. 13Claude Opus 4.8 (high)1503
  14. 14Kimi K3 (max)1503
  15. 15Claude Opus 5 (max)1502
355 of 355
#
1NewGemini 4 Carbonhigh154269.12026-10-28
2Gemini 4 Argonhigh153965.92026-10-28
3Claude Opus 5.5high152565.82026-10-28
4Claude Fable 5high152264.32026-10-28
5Claude Opus 4.6high152162.62026-10-28
6Claude Opus 4.6151662.32026-10-28
7Claude Opus 4.7high151560.92026-10-28
8Claude Fable 5.1max151267.22026-10-28
9Gemini 3.8 Flashhigh151262.02026-10-28
10Claude Opus 4.7150863.12026-10-28
11Muse Wondermax150562.22026-10-28
12Claude Opus 5high150464.32026-10-28
13Claude Opus 4.8high150360.62026-10-28
14Kimi K3max150362.12026-10-28
15Claude Opus 5max150265.42026-10-28
16Gemini 3.7 Flashhigh150162.22026-10-28
17Claude Opus 4.8149960.02026-10-28
18Claude Sonnet 5.5xhigh149963.42026-10-28
19Gemini 3.1 Pro149960.52026-10-28
20GPT-5.6 Solxhigh149864.22026-10-28
21Muse Spark 1.3max149661.92026-10-28
22MiMo-V2.6-Pro149557.32026-10-28
23Claude Opus 4.5high149559.12026-10-28
24Claude Opus 4.5149257.92026-10-28
25Claude Sonnet 4.6149258.32026-10-28
26Qwen3.8 Maxmax149258.82026-10-28
27GPT-6.1 Solmax149167.22026-10-28
28Gemini 3 Pro149060.22026-10-28
29Qwen3.7max149060.32026-10-28
30Muse Spark 1.2xhigh148961.72026-10-28
31GPT-6 Astramax148867.82026-10-28
32GPT-5.5high148763.72026-10-28
33GPT-5.5148761.72026-10-28
34GLM 5.3max148659.02026-10-28
35MiMo-V2.5-Pro148654.92026-10-28
36GLM 5.2max148660.22026-10-28
37Claude Sonnet 4.5high148657.92026-10-28
38Gemini 3.6 Flashhigh148561.32026-10-28
39Claude Opus 4.1thinking148557.92026-10-28
40Gemini 3.5 Flashhigh148262.62026-10-28
41GLM 5.3 Flash148256.82026-10-28
42Claude Sonnet 4.5148253.72026-10-28
43Claude Sonnet 5high148159.32026-10-28
44Qwen3.5 Maxmax1481–2026-10-28
45GPT-5.4high148158.82026-10-28
46Gemini 3.5 Flashmedium148161.92026-10-28
47DeepSeek V4.1 Flashmax148159.02026-10-28
48Muse Spark 1.1148062.22026-10-28
49GLM 5.1148055.82026-10-28
50Grok 4.5148059.82026-10-28
51Kimi K2.6147855.22026-10-28
52GPT-5.4147758.02026-10-28
53Muse Spark147664.22026-10-28
54Gemini 3 Flash147657.02026-10-28
55GPT-5.5 Instant147557.02026-10-28
56DeepSeek V4 Prohigh147557.52026-10-28
57Grok 4.6high147460.52026-10-28
58Qwen3.6 Maxmax147362.42026-10-28
59GPT-5.2147257.92026-10-28
60Claude Opus 4.1147251.42026-10-28

More human preference benchmarks · All LLM benchmarks

Related benchmarks

Top head-to-heads on Arena Longer Queries

Cite as: BenchLeader, “Arena Longer Queries leaderboard”, data as of 5 Nov 2026, https://www.benchleader.com/benchmarks/lmarena_text_longer.

Arena Longer Queries: questions

What does Arena Longer Queries measure?
Pairwise votes on prompts above a length threshold. Scores are reported in Elo-style ratings from pairwise comparisons; higher is better.
What is the top score on LMArena Longer Queries?
As of 5 Nov 2026, the highest score on Arena Longer Queries is 1542 by Gemini 4 Carbon (result dated 28 Oct 2026), ahead of Gemini 4 Argon at 1539. Scores come from Arena (LMArena) and are re-read daily.
Which AI model leads Arena Longer Queries?
Gemini 4 Carbon leads Arena Longer Queries with 1542 as of 5 Nov 2026 (result dated 28 Oct 2026), ahead of Gemini 4 Argon at 1539.
How many models have Arena Longer Queries results?
355 model configurations have a Arena Longer Queries result on BenchLeader, all taken from Arena (LMArena).
Who runs Arena Longer Queries and how often is it updated?
Arena Longer Queries is published by Arena (LMArena). BenchLeader re-reads the published results once a day and records the date each result was published.
Does Arena Longer Queries count toward the BenchLeader Index?
No. Arena Longer Queries is shown for reference but left out of the composite index.