BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases7

LMCA leaderboard

As of 6 Nov 2026, the top score on LMCA is 68.3% by Claude Sonnet 5.5 (Anthropic), ahead of Claude Opus 5.5 at 68.2%, across 193 model configurations with a published result (Epoch AI Benchmarking Hub, result dated 28 Sep 2026). A broad assessment scored 0 to 100 with a ceiling of 85 for the current version. LMCA is shown for reference only and does not count toward the BenchLeader Index.

Key facts (as of 6 Nov 2026)

  • Claude Sonnet 5.5 holds the top LMCA score at 68.3% (Epoch AI Benchmarking Hub, 28 Sep 2026).
  • Claude Opus 5.5 is second on LMCA at 68.2% (Epoch AI Benchmarking Hub, 22 Sep 2026).
  • LMCA: A capability assessment with a published score ceiling (Epoch AI Benchmarking Hub).
  • 193 model configurations have a published LMCA result on BenchLeader (BenchLeader, 6 Nov 2026).
  • LMCA does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).

A capability assessment with a published score ceiling.

Published by
Epoch AI Benchmarking Hub
Category
Reasoning
Index weight
Reference only
Models
193
Data as of
6 Nov 2026

CC BY 4.0 — Epoch AI, ‘AI Benchmarking Hub’, epoch.ai/benchmarks. Mirrored boards credit their original publishers.

What the test looks like

A broad assessment scored 0 to 100 with a ceiling of 85 for the current version.

How it is scored

Score, as published.

What to keep in mind

The ceiling means top scores compress; new.

Top 15
  1. 1Claude Sonnet 5.5 (max)68.3%
  2. 2Claude Opus 5.5 (max)68.2%
  3. 3Claude Sonnet 5.5 (xhigh)66.3%
  4. 4Claude Opus 5.5 (xhigh)66.2%
  5. 5Claude Sonnet 5.5 (high)65.9%
  6. 6Claude Opus 5.5 (high)65.9%
  7. 7Claude Opus 5.5 (medium)65.7%
  8. 8Claude Fable 5.165.5%
  9. 9Claude Sonnet 5.5 (medium)65.5%
  10. 10Claude Fable 5.1 (medium)65.3%
  11. 11Claude Fable 5.1 (high)65.1%
  12. 12Claude Fable 5.1 (xhigh)65.1%
  13. 13Claude Opus 5.5 (low)64.9%
  14. 14Claude Sonnet 5.5 (low)64.5%
  15. 15Claude Opus 5 (xhigh)64.5%
193 of 193
#
1Claude Sonnet 5.5max68.3%65.42026-09-28
2Claude Opus 5.5max68.2%69.32026-09-22
3Claude Sonnet 5.5xhigh66.3%63.42026-09-28
4Claude Opus 5.5xhigh66.2%66.32026-09-22
5Claude Sonnet 5.5high65.9%58.62026-09-28
6Claude Opus 5.5high65.9%65.82026-09-22
7Claude Opus 5.5medium65.7%62.02026-09-22
8Claude Fable 5.165.5%66.42026-09-01
9Claude Sonnet 5.5medium65.5%51.22026-09-28
10Claude Fable 5.1medium65.3%62.32026-09-01
11Claude Fable 5.1high65.1%64.02026-09-01
12Claude Fable 5.1xhigh65.1%65.42026-09-01
13Claude Opus 5.5low64.9%59.52026-09-22
14Claude Sonnet 5.5low64.5%51.32026-09-28
15Claude Opus 5xhigh64.5%60.22026-07-24
16GPT-6 Astraxhigh64.4%66.82026-09-03
17GPT-6 Astra64.1%68.22026-09-03
18GPT-6 Astrahigh63.8%67.02026-09-03
19Gemini 4 Argonhigh63.7%66.02026-09-30
20Claude Opus 5high63.7%64.32026-07-24
21Claude Fable 5.1low63.5%59.32026-09-01
22Claude Opus 5max63.3%65.42026-07-24
23GPT-6 Astramedium62.9%65.12026-09-03
24Claude Opus 5medium62.9%57.42026-07-24
25Gemini 4 Argonlow62.9%–2026-09-30
26Gemini 4 Argonmedium62.9%–2026-09-30
27GPT-6.1 Solmax62.8%67.32026-09-29
28Claude Opus 5low62.6%57.02026-07-24
29GPT-6 Astralow62.2%62.72026-09-03
30Claude Fable 5high61.1%64.32026-06-09
31Claude Fable 5xhigh61.0%–2026-06-09
32Claude Fable 5max60.3%65.32026-06-09
33Claude Fable 5medium60.3%–2026-06-09
34Claude Fable 5low59.6%–2026-06-09
35GPT-5.6 Solpro mode59.2%–2026-07-09
36GPT-6 Solmax59.1%63.32026-09-22
37GPT-5.6 Solxhigh58.5%64.22026-07-09
38GPT-5.6 Solmax58.4%65.42026-07-09
39Claude Opus 4.8max57.5%60.22026-05-28
40GPT-5.6 Solhigh56.9%63.62026-07-09
41Muse Wonder56.8%63.92026-10-12
42GPT-5.6 Solmedium56.4%61.52026-07-09
43GPT-5.6 Sollow55.9%60.42026-07-09
44Claude Opus 4.6max55.8%55.82026-02-05
45GLM 5.355.5%–2026-08-14
46GPT-5.6 Terramax55.0%60.72026-07-09
47GPT-5.5xhigh54.3%64.32026-04-23
48GPT-5.5 Proxhigh53.9%–2026-04-23
49Muse Spark 1.353.9%57.72026-09-02
50Gemini 3.1 Prohigh53.8%60.12026-02-19
51Gemini 3.8 Flashmedium52.9%60.72026-09-02
52Gemini 3.1 Promedium52.8%–2026-02-19
53GPT-5.6 Solno reasoning52.8%52.22026-07-09
54Kimi K3max52.7%62.12026-07-16
55GPT-5.6 Terraxhigh52.2%60.32026-07-09
56Claude Opus 4.7max52.2%59.52026-04-16
57GPT-5.4xhigh52.0%63.22026-03-05
58Gemini 3.8 Flash51.5%54.42026-09-02
59GPT-5.6 Terrahigh51.4%57.02026-07-09
60Gemini 3.1 Prolow51.2%–2026-02-19

More reasoning benchmarks · All LLM benchmarks

Related benchmarks

Top head-to-heads on LMCA

Cite as: BenchLeader, “LMCA leaderboard”, data as of 6 Nov 2026, https://www.benchleader.com/benchmarks/lmca.

LMCA: questions

What does LMCA measure?
A broad assessment scored 0 to 100 with a ceiling of 85 for the current version. Scores are reported in percent of tasks solved; higher is better.
What is the top score on LMCA?
As of 6 Nov 2026, the highest score on LMCA is 68.3% by Claude Sonnet 5.5 (result dated 28 Sep 2026), ahead of Claude Opus 5.5 at 68.2%. Scores come from Epoch AI Benchmarking Hub and are re-read daily.
Which AI model leads LMCA?
Claude Sonnet 5.5 leads LMCA with 68.3% as of 6 Nov 2026 (result dated 28 Sep 2026), ahead of Claude Opus 5.5 at 68.2%.
How many models have LMCA results?
193 model configurations have a LMCA result on BenchLeader, all taken from Epoch AI Benchmarking Hub.
Who runs LMCA and how often is it updated?
LMCA is published by Epoch AI Benchmarking Hub. BenchLeader re-reads the published results once a day and records the date each result was published.
Does LMCA count toward the BenchLeader Index?
No. LMCA is shown for reference but left out of the composite index.