BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases12

MLCR leaderboard

As of 9 Nov 2026, the top score on MLCR is 41.7%, shared by GPT-6 Astra and Claude Sonnet 5.5, ahead of GPT-6.1 Sol at 38.3%, across 174 model configurations with a published result (Artificial Analysis, result dated 3 Sep 2026). Medical long-context reasoning: clinical questions answered over long patient records, scored on accuracy, completeness and concision together. MLCR is shown for reference only and does not count toward the BenchLeader Index.

Key facts (as of 9 Nov 2026)

  • GPT-6 Astra and Claude Sonnet 5.5 share the top MLCR score at 41.7% (Artificial Analysis, 9 Nov 2026).
  • MLCR: Medical long-context reasoning: clinical questions answered over long patient records, scored on accuracy, completeness and concision together (Artificial Analysis).
  • 174 model configurations have a published MLCR result on BenchLeader (BenchLeader, 9 Nov 2026).
  • MLCR does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).

Medical long-context reasoning: clinical questions answered over long patient records, scored on accuracy, completeness and concision together.

Published by
Artificial Analysis
Category
Long context
Index weight
Reference only
Models
174
Data as of
9 Nov 2026

Source: Artificial Analysis (artificialanalysis.ai). Data taken from the public leaderboard.

Top 15
  1. 1GPT-6 Astra (max)41.7%
  2. 2Claude Sonnet 5.5 (max)41.7%
  3. 3GPT-6.1 Sol (max)38.3%
  4. 4GPT-6 Astra (medium)38.3%
  5. 5Kimi K3.1 Pro38.3%
  6. 6GPT-6 Astra (xhigh)36.1%
  7. 7GPT-6.1 Sol (xhigh)35.6%
  8. 8Claude Haiku 5.5 (max)35.0%
  9. 9GPT-6 Sol (max)33.9%
  10. 10GPT-6 Astra (low)33.9%
  11. 11GPT-6 Astra (high)32.8%
  12. 12GPT-6.1 Sol (medium)32.2%
  13. 13GPT-6 Sol (xhigh)32.2%
  14. 14GPT-6.1 Sol (high)31.7%
  15. 15GPT-5.5 Instant31.7%
174 of 174
#
1GPT-6 Astramax41.7%67.42026-09-03
2Claude Sonnet 5.5max41.7%65.02026-09-28
3GPT-6.1 Solmax38.3%67.02026-09-29
4GPT-6 Astramedium38.3%64.52026-09-03
5Kimi K3.1 Pro38.3%61.22026-10-23
6GPT-6 Astraxhigh36.1%66.22026-09-03
7GPT-6.1 Solxhigh35.6%63.82026-09-29
8Claude Haiku 5.5max35.0%56.82026-10-07
9GPT-6 Solmax33.9%62.92026-09-22
10GPT-6 Astralow33.9%62.22026-09-03
11GPT-6 Astrahigh32.8%66.52026-09-03
12GPT-6.1 Solmedium32.2%62.92026-09-29
13GPT-6 Solxhigh32.2%58.62026-09-22
14GPT-6.1 Solhigh31.7%63.52026-09-29
15GPT-5.5 Instant31.7%57.02026-06-25
16GPT-6.1 Terramax30.6%65.02026-10-26
17Qwen3.8 2.4T A95B30.6%51.62026-08-12
18GPT-5.6 Solmax30.0%65.42026-07-09
19GPT-6 Solhigh29.4%58.22026-09-22
20GPT-5.5xhigh28.9%64.32026-04-23
21GPT-6 Solmedium28.9%57.02026-09-22
22Claude Opus 5.5max27.8%68.92026-09-22
23GPT-5.6 Solxhigh27.8%64.22026-07-09
24GPT-5.6 Terramax27.2%60.52026-07-09
25GPT-6.1 Sollow26.7%60.22026-09-29
26DeepSeek V4.1 Flash 1017max26.7%58.92026-10-17
27GPT-5.6 Solmedium26.1%61.42026-07-09
28Qwen3.8 Maxmax26.1%58.92026-08-03
29GPT-6 Lunamax26.1%56.52026-09-22
30GPT-6 Sollow25.6%54.62026-09-22
31Claude Opus 5.5xhigh25.0%65.52026-09-22
32GPT-5.5high25.0%63.72026-04-23
33GPT-5.6 Solhigh24.4%63.52026-07-09
34DeepSeek V4.1 Flashmax23.9%58.92026-09-10
35GPT-5.6 Sollow23.3%60.32026-07-09
36GPT-5.6 Terraxhigh22.8%60.32026-07-09
37GPT-5.6 Terramedium22.8%52.82026-07-09
38Qwen3.8 27Bxhigh22.8%52.42026-08-14
39GPT-6 Solno reasoning22.8%49.12026-09-22
40Muse Wonder Fullmax22.2%62.22026-10-12
41Muse Wondermax22.2%61.92026-10-12
42Claude Opus 5.5medium22.2%61.52026-09-22
43GPT-5.5medium22.2%60.92026-04-23
44Kimi K3max21.7%62.02026-07-16
45Grok 4.7low21.1%55.52026-09-21
46Claude Fable 5max20.6%65.32026-06-09
47Claude Sonnet 5.5xhigh20.6%62.72026-09-28
48Qwen3.8-Flash-Next20.6%54.42026-08-26
49GPT-6 Lunaxhigh20.6%52.12026-09-22
50Grok 4.7xhigh20.0%58.12026-09-21
51GPT-5.6 Lunamax20.0%56.22026-07-09
52GPT-5.4 Minixhigh20.0%56.02026-03-17
53GPT-5.6 Terralow20.0%53.42026-07-09
54Claude Opus 4.8max19.4%60.22026-05-28
55Claude Opus 5.5low19.4%59.02026-09-22
56GPT-6 Lunahigh19.4%51.22026-09-22
57Claude Sonnet 5.5low19.4%50.82026-09-28
58Claude Sonnet 5.5high18.9%58.02026-09-28
59Grok 4.7high18.9%57.02026-09-21
60GPT-5.6 Terrahigh18.9%56.92026-07-09

More long context benchmarks · All LLM benchmarks

Related benchmarks

Top head-to-heads on MLCR

Cite as: BenchLeader, “MLCR leaderboard”, data as of 9 Nov 2026, https://www.benchleader.com/benchmarks/aa_mlcr.

MLCR: questions

What does MLCR measure?
Medical long-context reasoning: clinical questions answered over long patient records, scored on accuracy, completeness and concision together. Scores are reported in percent of tasks solved; higher is better.
What is the top score on MLCR?
As of 9 Nov 2026, the highest score on MLCR is 41.7%, shared by GPT-6 Astra and Claude Sonnet 5.5, ahead of GPT-6.1 Sol at 38.3%. Scores come from Artificial Analysis and are re-read daily.
Which AI model leads MLCR?
GPT-6 Astra and Claude Sonnet 5.5 tie for first on MLCR at 41.7% as of 9 Nov 2026, ahead of GPT-6.1 Sol at 38.3%.
How many models have MLCR results?
174 model configurations have a MLCR result on BenchLeader, all taken from Artificial Analysis.
Who runs MLCR and how often is it updated?
MLCR is published by Artificial Analysis. BenchLeader re-reads the published results once a day and records the date each result was published.
Does MLCR count toward the BenchLeader Index?
No. MLCR is shown for reference but left out of the composite index.