Skip to main content

Benchmark profile

Vals MedScribe (MedScribe)

Vals AI healthcare benchmark for whether models can support doctors with administrative work.

Data verified

How BenchLM shows MedScribe

BenchLM mirrors the public Vals AI MedScribe leaderboard captured from https://www.vals.ai/benchmarks/medscribe and updated by Vals on July 23, 2026. The snapshot preserves overall scores, uncertainty, latency, cost-per-test metadata, and task-level scores where Vals publishes them.

MedScribe is display only on BenchLM. Vals proprietary or Vals-hosted aggregate views are useful context, but BenchLM does not use them as weighted ranking inputs or as a replacement for benchmark-native source records.

75 Vals rows1 task viewsprivate datasetTasks: OverallDisplay only

MedScribe score on MedScribe — July 23, 2026

BenchLM mirrors the published medscribe score view for MedScribe. Claude Opus 5 leads the public snapshot at 90.98% , followed by Muse Spark 1.1 (88.89%) and Claude Fable 5 (88.52%). BenchLM does not use these results to rank models overall.

75 modelsExternal benchmark mirrorsCurrentDisplay onlyUpdated July 23, 2026

MedScribe score table (75 models)

Score
1
Claude Opus 5Anthropic
90.98%
2
88.89%
3
88.52%
4
GPT-5.1OpenAI
88.09%
5
Kimi K3Moonshot AI
87.96%
6
MiniMax M3MiniMax
87.25%
7
86.88%
8
GPT-5.5OpenAI
86.87%
9
86.74%
10
86.13%
11
85.90%
12
85.75%
13
InklingThinkingmachines
85.41%
15
85.23%
17
84.52%
18
84.39%
19
GPT-5.2OpenAI
84.39%
21
83.73%
22
GPT-5OpenAI
83.65%
23
GLM 5.2Zhipu AI
83.53%
24
83.25%
26
82.95%
27
82.87%
28
82.87%
30
80.78%
31
80.58%
32
79.87%
34
79.66%
35
79.40%
38
78.15%
39
Kimi K2.6Moonshot AI
78.15%
41
GPT-5.4OpenAI
77.55%
43
77.13%
44
77.09%
45
76.96%
46
O3OpenAI
76.65%
47
76.57%
48
76.44%
50
76.05%
52
75.14%
53
74.40%
55
73.55%
56
72.86%
57
72.83%
58
Qwen3 MaxAlibaba
72.71%
59
72.41%
60
GLM 5.1Zhipu AI
72.27%
61
Mimo V2.5Xiaomi
72.15%
62
72.04%
63
71.75%
64
70.89%
65
70.62%
68
O4 MiniOpenAI
69.14%
69
GLM 4.7Zhipu AI
68.63%
70
67.73%
74
54.22%

The published MedScribe snapshot places Claude Opus 5 first at 90.98%. The third row is 2.46 points behind. The broader top-10 range is 4.86 points, so many of the published results sit in a relatively narrow band.

75 models have been evaluated on MedScribe. The benchmark falls in the External benchmark mirrors category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. MedScribe is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About MedScribe

Year

2026

Tasks

Medical administrative support tasks

Format

Accuracy score

Difficulty

Professional healthcare administration

BenchLM mirrors the public Vals MedScribe leaderboard as display-only healthcare evidence.

BenchLM freshness & provenance

Version

MedScribe 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does MedScribe measure?

Vals AI healthcare benchmark for whether models can support doctors with administrative work.

Which model leads the published MedScribe snapshot?

Claude Opus 5 currently leads the published MedScribe snapshot with 90.98% medscribe score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on MedScribe?

75 AI models are included in BenchLM's mirrored MedScribe snapshot, based on the public leaderboard captured on July 23, 2026.

Last updated: July 23, 2026 · mirrored from the public benchmark leaderboard

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.