# MedScribe / overall > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/vals-ai%3Amedscribe%3Aoverall. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/vals-ai%3Amedscribe%3Aoverall. Can models support doctors with their administrative work? Canonical URL: https://benchize.com/benchmarks/vals-ai%3Amedscribe%3Aoverall Last updated: Wed, 21 Oct 2026 18:52:20 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Can models support doctors with their administrative work? Professional work · Models tested: 49 · Score publishers: Vals AI ## Model results | # | Model | Score | ± | Cost | Latency | | | --- | --- | --- | --- | --- | --- | --- | | 1 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max | 91.43% | SE ±1.93 pp | $1.15 | 441.58source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.43 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.154156 \| USD \| per_test \| Lower is better \| \| `latency` \| 441.582 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.93 pp sourcePopulation 109 stderr 1.932 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/anthropic~1claude-opus-5-5` | | | | | | | | 2 | [Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max | 91.29% | SE ±1.95 pp | $0.96 | 188.36source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.294 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.9635 \| USD \| per_test \| Lower is better \| \| `latency` \| 188.363 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.95 pp sourcePopulation 109 stderr 1.953 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label anthropic/claude-fable-5-1 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/anthropic~1claude-fable-5-1` | | | | | | | | 3 | [Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max | 91.1% | SE ±1.96 pp | $0.51 | 306.81source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.101 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.508604 \| USD \| per_test \| Lower is better \| \| `latency` \| 306.811 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.96 pp sourcePopulation 109 stderr 1.96 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label anthropic/claude-sonnet-5-5 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/anthropic~1claude-sonnet-5-5` | | | | | | | | 4 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max | 90.99% | SE ±1.92 pp | $0.24 | 76.56source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.985 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.236275 \| USD \| per_test \| Lower is better \| \| `latency` \| 76.563 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 30000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.92 pp sourcePopulation 109 stderr 1.916 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/anthropic~1claude-opus-5` | | | | | | | | 5 | [Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high | 90.06% | SE ±1.96 pp | $0.04 | 61.46source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.062 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.037779 \| USD \| per_test \| Lower is better \| \| `latency` \| 61.458 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Meta reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.96 pp sourcePopulation 109 stderr 1.958 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label meta/muse_spark_1_2 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/meta~1muse_spark_1_2` | | | | | | | | 6 | [Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-max.md)Max | 89.54% | SE ±1.92 pp | $0.04 | 323.4source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.542 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.043777 \| USD \| per_test \| Lower is better \| \| `latency` \| 323.396 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.92 pp sourcePopulation 109 stderr 1.917 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/anthropic~1claude-haiku-5-5` | | | | | | | | 7 | [Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1-xhigh.md)Extra high | 88.89% | SE ±1.95 pp | $0.03 | 63.34source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.888 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.034628 \| USD \| per_test \| Lower is better \| \| `latency` \| 63.335 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Meta reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.95 pp sourcePopulation 109 stderr 1.95 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label meta/muse_spark_1_1 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/meta~1muse_spark_1_1` | | | | | | | | 8 | [Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max | 88.52% | SE ±1.95 pp | $0.58 | 119.48source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.522 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.583239 \| USD \| per_test \| Lower is better \| \| `latency` \| 119.475 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 30000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.95 pp sourcePopulation 109 stderr 1.945 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label anthropic/claude-fable-5 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/anthropic~1claude-fable-5` | | | | | | | | 9 | [MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md) | 88.31% | SE ±1.94 pp | $0.00988 | 173.35source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.307 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.00988 \| USD \| per_test \| Lower is better \| \| `latency` \| 173.345 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.94 pp sourcePopulation 109 stderr 1.938 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label xiaomi/mimo-v2.6-pro Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/xiaomi~1mimo-v2.6-pro` | | | | | | | | 10 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max | 87.91% | SE ±1.94 pp | $0.58 | 153.73source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.908 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.581991 \| USD \| per_test \| Lower is better \| \| `latency` \| 153.728 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.94 pp sourcePopulation 109 stderr 1.938 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/openai~1gpt-6-astra` | | | | | | | | 11 | [Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High | 87.43% | SE ±1.96 pp | $0.15 | 87.44source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.427 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.147175 \| USD \| per_test \| Lower is better \| \| `latency` \| 87.439 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.96 pp sourcePopulation 109 stderr 1.964 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/google~1gemini-4-argon` | | | | | | | | 12 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 87.25% | SE ±1.96 pp | $0.01 | 123.97source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.252 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.013748 \| USD \| per_test \| Lower is better \| \| `latency` \| 123.967 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.96 pp sourcePopulation 109 stderr 1.957 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/minimax~1MiniMax-M3` | | | | | | | | 13 | [GPT-5.5](https://benchize.com/models/gpt-5-5-xhigh.md)Extra high | 86.87% | SE ±1.93 pp | $0.14 | 132.76source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.868 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.142988 \| USD \| per_test \| Lower is better \| \| `latency` \| 132.761 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.93 pp sourcePopulation 109 stderr 1.932 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/openai~1gpt-5.5` | | | | | | | | 14 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6-max.md)Max | 86.74% | SE ±1.94 pp | $0.12 | 54.32source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.738 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.115121 \| USD \| per_test \| Lower is better \| \| `latency` \| 54.318 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 30000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.94 pp sourcePopulation 109 stderr 1.942 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label anthropic/claude-opus-4-6 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/anthropic~1claude-opus-4-6` | | | | | | | | 15 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max | 86.45% | SE ±1.9 pp | $0.1 | 169.62source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.453 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.100902 \| USD \| per_test \| Lower is better \| \| `latency` \| 169.619 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.9 pp sourcePopulation 109 stderr 1.898 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label openai/gpt-6.1-sol Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/openai~1gpt-6.1-sol` | | | | | | | | 16 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-max.md)Max | 85.76% | SE ±1.93 pp | $0.26 | 82.36source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.755 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.259121 \| USD \| per_test \| Lower is better \| \| `latency` \| 82.364 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 30000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.93 pp sourcePopulation 109 stderr 1.928 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label anthropic/claude-opus-4-8 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/anthropic~1claude-opus-4-8` | | | | | | | | 17 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash-high.md)High | 85.5% | SE ±1.92 pp | $0.02 | 53.83source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.5 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.015397 \| USD \| per_test \| Lower is better \| \| `latency` \| 53.826 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.92 pp sourcePopulation 109 stderr 1.918 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label deepseek/deepseek-v4.1-flash Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/deepseek~1deepseek-v4.1-flash` | | | | | | | | 18 | [MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md) | 85.28% | SE ±1.99 pp | $0.00218 | 74.48source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.275 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002184 \| USD \| per_test \| Lower is better \| \| `latency` \| 74.481 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.99 pp sourcePopulation 109 stderr 1.986 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label xiaomi/mimo-v2.6-flash Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/xiaomi~1mimo-v2.6-flash` | | | | | | | | 19 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-max.md)Max | 85.23% | SE ±1.97 pp | $0.28 | 94.4source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.233 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.276691 \| USD \| per_test \| Lower is better \| \| `latency` \| 94.404 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.97 pp sourcePopulation 109 stderr 1.973 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label openai/gpt-5.6-sol Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/openai~1gpt-5.6-sol` | | | | | | | | 20 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 84.5% | SE ±1.94 pp | $0.03 | 21.15source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84.496 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.025238 \| USD \| per_test \| Lower is better \| \| `latency` \| 21.145 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.94 pp sourcePopulation 109 stderr 1.943 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label google/gemini-3.8-flash Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/google~1gemini-3.8-flash` | | | | | | | | 21 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna-max.md)Max | 84.39% | SE ±2.59 pp | $0.02 | 116.89source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84.391 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.022813 \| USD \| per_test \| Lower is better \| \| `latency` \| 116.886 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.59 pp sourcePopulation 109 stderr 2.585 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label openai/gpt-5.6-luna Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/openai~1gpt-5.6-luna` | | | | | | | | 22 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-high.md)High | 83.94% | SE ±2 pp | $0.06 | 16.82source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.942 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.058736 \| USD \| per_test \| Lower is better \| \| `latency` \| 16.818 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2 pp sourcePopulation 109 stderr 2.004 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label google/gemini-3.7-flash Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/google~1gemini-3.7-flash` | | | | | | | | 23 | [MiMo-V2.5-Pro](https://benchize.com/models/mimo-v2-5-pro.md) | 83.73% | SE ±2.06 pp | $0.00603 | 90.71source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.73 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.00603 \| USD \| per_test \| Lower is better \| \| `latency` \| 90.71 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.06 pp sourcePopulation 109 stderr 2.063 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label xiaomi/mimo-v2.5-pro Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/xiaomi~1mimo-v2.5-pro` | | | | | | | | 24 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max | 83.71% | SE ±1.95 pp | $0.00956 | 169.61source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.71 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.009562 \| USD \| per_test \| Lower is better \| \| `latency` \| 169.606 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.95 pp sourcePopulation 109 stderr 1.949 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label openai/gpt-6-luna Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/openai~1gpt-6-luna` | | | | | | | | 25 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-max.md)Max | 82.95% | SE ±1.98 pp | $0.18 | 67.5source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.953 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.177841 \| USD \| per_test \| Lower is better \| \| `latency` \| 67.496 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 30000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.98 pp sourcePopulation 109 stderr 1.977 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label anthropic/claude-opus-4-7 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/anthropic~1claude-opus-4-7` | | | | | | | | 26 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra-xhigh.md)Extra high | 82.87% | SE ±1.95 pp | $0.06 | 35.53source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.869 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.062588 \| USD \| per_test \| Lower is better \| \| `latency` \| 35.526 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.95 pp sourcePopulation 109 stderr 1.948 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label openai/gpt-5.6-terra Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/openai~1gpt-5.6-terra` | | | | | | | | 26 | [Gemini 2.5 Flash](https://benchize.com/models/gemini-2-5-flash.md) | 82.87% | SE ±1.91 pp | $0.01 | 22.79source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.869 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.014869 \| USD \| per_test \| Lower is better \| \| `latency` \| 22.786 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.91 pp sourcePopulation 109 stderr 1.909 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label google/gemini-2.5-flash Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/google~1gemini-2.5-flash` | | | | | | | | 28 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol-max.md)Max | 82.03% | SE ±1.94 pp | $0.08 | 81.14source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.034 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.083138 \| USD \| per_test \| Lower is better \| \| `latency` \| 81.135 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.94 pp sourcePopulation 109 stderr 1.942 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label openai/gpt-6-sol Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/openai~1gpt-6-sol` | | | | | | | | 29 | [MiniMax M2.1](https://benchize.com/models/minimax-m2-1.md) | 80.78% | SE ±1.83 pp | $0.00509 | 53.16source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.777 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005087 \| USD \| per_test \| Lower is better \| \| `latency` \| 53.161 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.83 pp sourcePopulation 109 stderr 1.831 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label minimax/MiniMax-M2.1 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/minimax~1MiniMax-M2.1` | | | | | | | | 30 | [DeepSeek V4 Flash 0731](https://benchize.com/models/deepseek-v4-flash-0731-high.md)High | 80.36% | SE ±1.97 pp | $0.01 | 77.55source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.363 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.014247 \| USD \| per_test \| Lower is better \| \| `latency` \| 77.552 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider DeepSeek reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.97 pp sourcePopulation 109 stderr 1.973 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label deepseek/deepseek-v4-flash-0731 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/deepseek~1deepseek-v4-flash-0731` | | | | | | | | 31 | [DeepSeek V4 Pro 0813](https://benchize.com/models/deepseek-v4-pro-0813-max.md)Max | 80.17% | SE ±2 pp | $0.04 | 155.86source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.174 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.041127 \| USD \| per_test \| Lower is better \| \| `latency` \| 155.859 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2 pp sourcePopulation 109 stderr 2.004 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/deepseek~1deepseek-v4-pro-0813` | | | | | | | | 32 | [MiniMax M2.7](https://benchize.com/models/minimax-m2-7.md) | 79.87% | SE ±1.86 pp | $0.00512 | 27.25source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.867 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005124 \| USD \| per_test \| Lower is better \| \| `latency` \| 27.25 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.86 pp sourcePopulation 109 stderr 1.86 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label minimax/MiniMax-M2.7 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/minimax~1MiniMax-M2.7` | | | | | | | | 33 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash-high.md)High | 79.66% | SE ±1.86 pp | $0.07 | 33.55source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.661 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.073178 \| USD \| per_test \| Lower is better \| \| `latency` \| 33.552 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.86 pp sourcePopulation 109 stderr 1.861 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/google~1gemini-3.6-flash` | | | | | | | | 34 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High | 76.57% | SE ±1.92 pp | $0.17 | 57.08source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 76.574 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.166341 \| USD \| per_test \| Lower is better \| \| `latency` \| 57.075 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.92 pp sourcePopulation 109 stderr 1.923 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label google/gemini-3.5-flash Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/google~1gemini-3.5-flash` | | | | | | | | 35 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High | 76.11% | SE ±1.92 pp | $0.1 | 69.14source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 76.114 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.097954 \| USD \| per_test \| Lower is better \| \| `latency` \| 69.139 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.92 pp sourcePopulation 109 stderr 1.915 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label google/gemini-3.1-pro-preview Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/google~1gemini-3.1-pro-preview` | | | | | | | | 36 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5-max.md)Max | 76.05% | SE ±3.05 pp | $0.43 | 251.7source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 76.054 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.433684 \| USD \| per_test \| Lower is better \| \| `latency` \| 251.703 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 30000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.05 pp sourcePopulation 109 stderr 3.05 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label anthropic/claude-sonnet-5 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/anthropic~1claude-sonnet-5` | | | | | | | | 37 | [Gemini 2.5 Flash Lite Preview 09-2025](https://benchize.com/models/gemini-2-5-flash-lite-preview-09-2025.md) | 75.82% | SE ±1.85 pp | $0.00133 | 4.49source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75.824 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.001332 \| USD \| per_test \| Lower is better \| \| `latency` \| 4.491 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.85 pp sourcePopulation 109 stderr 1.851 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label google/gemini-2.5-flash-lite-preview-09-2025 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/google~1gemini-2.5-flash-lite-preview-09-2025` | | | | | | | | 38 | [DeepSeek V4 Pro](https://benchize.com/models/deepseek-v4-pro-max.md)Max | 75.14% | SE ±2 pp | $0.05 | 345.72source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75.144 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.053954 \| USD \| per_test \| Lower is better \| \| `latency` \| 345.723 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2 pp sourcePopulation 109 stderr 2.002 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label deepseek/deepseek-v4-pro Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/deepseek~1deepseek-v4-pro` | | | | | | | | 39 | [Gemini 2.5 Pro](https://benchize.com/models/gemini-2-5-pro.md) | 73.55% | SE ±1.91 pp | $0.05 | 35.91source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 73.552 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.046379 \| USD \| per_test \| Lower is better \| \| `latency` \| 35.909 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.91 pp sourcePopulation 109 stderr 1.91 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label google/gemini-2.5-pro Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/google~1gemini-2.5-pro` | | | | | | | | 40 | [Gemini 2.5 Flash Lite](https://benchize.com/models/gemini-2-5-flash-lite.md) | 72.83% | SE ±1.98 pp | $0.00121 | 4.85source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 72.832 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.001211 \| USD \| per_test \| Lower is better \| \| `latency` \| 4.847 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.98 pp sourcePopulation 109 stderr 1.982 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label google/gemini-2.5-flash-lite Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/google~1gemini-2.5-flash-lite` | | | | | | | | 41 | [MiMo-V2.5](https://benchize.com/models/mimo-v2-5.md) | 72.15% | SE ±1.85 pp | $0.00135 | 20.26source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 72.151 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.001351 \| USD \| per_test \| Lower is better \| \| `latency` \| 20.261 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.85 pp sourcePopulation 109 stderr 1.851 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label xiaomi/mimo-v2.5 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/xiaomi~1mimo-v2.5` | | | | | | | | 42 | [Gemini 3.5 Flash-Lite](https://benchize.com/models/gemini-3-5-flash-lite-high.md)High | 70.89% | SE ±2.03 pp | $0.02 | 18.99source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.886 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.019867 \| USD \| per_test \| Lower is better \| \| `latency` \| 18.991 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.03 pp sourcePopulation 109 stderr 2.031 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label google/gemini-3.5-flash-lite Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/google~1gemini-3.5-flash-lite` | | | | | | | | 43 | [Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview-high.md)High | 69.92% | SE ±1.9 pp | $0.01 | 23.49source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.917 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.014379 \| USD \| per_test \| Lower is better \| \| `latency` \| 23.491 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.9 pp sourcePopulation 109 stderr 1.899 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label google/gemini-3-flash-preview Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/google~1gemini-3-flash-preview` | | | | | | | | 44 | [Mistral Medium 3.5](https://benchize.com/models/mistral-medium-3-5-high.md)High | 67.73% | SE ±2.01 pp | $0.16 | 104.05source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 67.728 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.157641 \| USD \| per_test \| Lower is better \| \| `latency` \| 104.053 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Mistral AI reasoning Not reported Reasoning effort high Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.01 pp sourcePopulation 109 stderr 2.011 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label mistralai/mistral-medium-3.5 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/mistralai~1mistral-medium-3.5` | | | | | | | | 45 | [Laguna M 1](https://benchize.com/models/laguna-m-1.md) | 65.91% | SE ±2.01 pp | $0.0022 | 111.82source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 65.911 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002202 \| USD \| per_test \| Lower is better \| \| `latency` \| 111.816 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Poolside reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.01 pp sourcePopulation 109 stderr 2.007 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label poolside/laguna-m.1 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/poolside~1laguna-m.1` | | | | | | | | 46 | [Gemini 3.1 Flash Lite Preview](https://benchize.com/models/gemini-3-1-flash-lite-preview-high.md)High | 63.9% | SE ±1.82 pp | $0.0022 | 16.79source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 63.902 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002195 \| USD \| per_test \| Lower is better \| \| `latency` \| 16.793 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.82 pp sourcePopulation 109 stderr 1.823 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label google/gemini-3.1-flash-lite-preview Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/google~1gemini-3.1-flash-lite-preview` | | | | | | | | 47 | [Laguna Xs 2](https://benchize.com/models/laguna-xs-2.md) | 61.43% | SE ±2.35 pp | $0.00113 | 68.82source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 61.432 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.001126 \| USD \| per_test \| Lower is better \| \| `latency` \| 68.824 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Poolside reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.35 pp sourcePopulation 109 stderr 2.349 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label poolside/laguna-xs.2 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/poolside~1laguna-xs.2` | | | | | | | | 48 | [Command A Plus](https://benchize.com/models/command-a-plus.md) | 55.68% | SE ±3.65 pp | $0.14 | 203.05source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 55.682 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.140316 \| USD \| per_test \| Lower is better \| \| `latency` \| 203.051 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 64000 provider Cohere reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.65 pp sourcePopulation 109 stderr 3.646 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label cohere/command-a-plus-05-2026 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/cohere~1command-a-plus-05-2026` | | | | | | | | 49 | [Mercury 2.5](https://benchize.com/models/mercury-2-5-high.md)High | 55.09% | SE ±2.1 pp | $0.00448 | 9.99source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 55.093 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004476 \| USD \| per_test \| Lower is better \| \| `latency` \| 9.992 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Inception reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.1 pp sourcePopulation 109 stderr 2.095 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label inception/mercury-2.5 Source version 1 Observed 2026-10-21T16:46:00.004Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/inception~1mercury-2.5` | | | | | | | --- Cite as: MedScribe / overall — Benchize, https://benchize.com/benchmarks/vals-ai%3Amedscribe%3Aoverall (retrieved 2026-10-21)