BenchLeader

LMArena Text Factuality leaderboard

As of 21 Nov 2026, the top score on LMArena Text Factuality is 1522 by Gemini 4 Carbon (Google), ahead of Gemini 4 Neon at 1509, across 188 model configurations with a published result (Arena (LMArena), result dated 19 Nov 2026). Text arena rating with a factuality check folded in at 25% weight: the web-verifiable claims in each answer are checked, and factual errors count against the model. LMArena Text Factuality is shown for reference only and does not count toward the BenchLeader Index.

Key facts (as of 21 Nov 2026)

  • Gemini 4 Carbon holds the top Arena Text Factuality score at 1522 (Arena (LMArena), 19 Nov 2026).
  • Gemini 4 Neon is second on Arena Text Factuality at 1509 (Arena (LMArena), 19 Nov 2026).
  • Arena Text Factuality: Text arena rating with a factuality check folded in at 25% weight: the web-verifiable claims in each answer are checked, and factual errors count against the model (Arena (LMArena)).
  • 188 model configurations have a published Arena Text Factuality result on BenchLeader (BenchLeader, 21 Nov 2026).
  • Arena Text Factuality does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).

Text arena rating with a factuality check folded in at 25% weight: the web-verifiable claims in each answer are checked, and factual errors count against the model.

Published by
Arena (LMArena)
Category
Knowledge
Index weight
Reference only
Models
188
Data as of
21 Nov 2026

This week on Arena Text Factuality

14 Nov 2026 to 21 Nov 2026, one row per model (its best setting on this board).

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

188 of 188
#
1Gemini 4 Carbonhigh152268.62026-11-19$4.00
2NewGemini 4 Neonhigh150968.02026-11-19$6.00
3Claude Opus 5.5high150565.52026-11-19$8.00
4Claude Fable 5.1max149966.42026-11-19$20.00
5Muse Wondermax149460.12026-11-19$8.00
6Gemini 4 Hydrogenhigh149464.82026-11-19$3.00
7Claude Opus 4.6high149362.42026-11-19$10.00
8Gemini 4 Argonhigh149264.82026-11-19$4.00
9Claude Opus 4.6148860.72026-11-19$10.00
10Claude Opus 5max148864.52026-11-19$10.00
11MiMo-V2.6-Pro148657.02026-11-19$0.544
12GPT-5.5high148563.42026-11-19$11.25
13GPT-5.4high148458.42026-11-19$5.63
14Claude Fable 5high148363.32026-11-19$20.00
15Claude Fable 5.2max148370.22026-11-19$16.00
16Gemini 3 Pro148260.32026-11-19$4.50
17GPT-5.5148160.82026-11-19$11.25
18Muse Spark 1.3max148160.12026-11-19$2.00
19Qwen3.7 Max148059.82026-11-19$3.75
20Muse Spark 1.2xhigh147961.42026-11-19$2.00
21Kimi K3.1 Promax147960.22026-11-19$4.00
22Gemini 3.5 Flashhigh147862.42026-11-19$3.38
23Claude Opus 4.7high147859.92026-11-19$10.00
24Claude Opus 5high147864.22026-11-19$10.00
25GPT-5.6 Solxhigh147663.72026-11-19$8.00
26Claude Opus 4.7147663.02026-11-19$10.00
27Gemini 3.7 Flashhigh147661.92026-11-19$1.50
28Qwen3.5 Max1475–2026-11-19–
29GPT-5.4147557.72026-11-19$5.63
30Claude Sonnet 5.5xhigh147362.42026-11-19$4.00
31Qwen3.8 Max147360.82026-11-19$3.00
32Gemini 3.6 Flashhigh147260.92026-11-19$1.50
33Gemini 3.1 Pro147259.52026-11-19$4.50
34Kimi K3max147159.72026-11-19$6.00
35Claude Opus 4.8high147060.22026-11-19$10.00
36GPT-6.1 Solmax147065.82026-11-19$4.00
37GPT-5.6 Terraxhigh146959.92026-11-19$4.50
38Gemini 3.8 Flashhigh146959.12026-11-19$1.50
39GLM 5.3max146958.62026-11-19$2.15
40Muse Spark146864.82026-11-19–
41Gemini 3 Flash146858.52026-11-19$1.13
42GPT-6 Astramax146866.82026-11-19$20.00
43DeepSeek V4.1 Flashmax146858.52026-11-19$0.525
44Gemini 3.5 Flashmedium146761.82026-11-19$3.38
45GPT-6 Lunamax146654.42026-11-19$0.200
46Grok 4.5146558.92026-11-19$3.00
47Claude Opus 4.8146558.52026-11-19$10.00
48MiMo-V2.5-Pro146455.52026-11-19$0.435
49Muse Spark 1.1146461.62026-11-19$2.00
50GLM 5.2max146358.82026-11-19$2.15
51Gemini 2.5 Pro146253.52026-11-19$3.44
52GLM 5.3 Flash146157.52026-11-19$0.238
53Claude Sonnet 4.6146158.32026-11-19$6.00
54GPT-5.6 Lunaxhigh146058.02026-11-19$0.450
55Claude Opus 4.5145956.92026-11-19$10.00
56Claude Opus 4.5high145959.62026-11-19$10.00
57GPT-5.1high145857.52026-11-19$3.44
58Grok 4.20 Multi-Agent145858.42026-11-19$1.56
59ERNIE 5.11457–2026-11-19–
60Kimi K2.6145655.02026-11-19$1.71

More knowledge benchmarks · All LLM benchmarks

Cite as: BenchLeader, “Arena Text Factuality leaderboard”, data as of 21 Nov 2026, https://www.benchleader.com/benchmarks/lmarena_text_factuality.

Arena Text Factuality: questions

What does Arena Text Factuality measure?
Text arena rating with a factuality check folded in at 25% weight: the web-verifiable claims in each answer are checked, and factual errors count against the model. Scores are reported in Elo-style ratings from pairwise comparisons; higher is better.
What is the top score on LMArena Text Factuality?
As of 21 Nov 2026, the highest score on Arena Text Factuality is 1522 by Gemini 4 Carbon (result dated 19 Nov 2026), ahead of Gemini 4 Neon at 1509. Scores come from Arena (LMArena) and are re-read daily.
Which AI model leads Arena Text Factuality?
Gemini 4 Carbon leads Arena Text Factuality with 1522 as of 21 Nov 2026 (result dated 19 Nov 2026), ahead of Gemini 4 Neon at 1509.
How many models have Arena Text Factuality results?
188 model configurations have a Arena Text Factuality result on BenchLeader, all taken from Arena (LMArena).
Who runs Arena Text Factuality and how often is it updated?
Arena Text Factuality is published by Arena (LMArena). BenchLeader re-reads the published results once a day and records the date each result was published.
Does Arena Text Factuality count toward the BenchLeader Index?
No. Arena Text Factuality is shown for reference but left out of the composite index.