Clinical Benchmarks

Grok 4.5

Released 8 Jul 2026$2 input, $6 output per million tokens500K contextproprietaryAlso written as Grok 4.5 (high), grok-4.5Compare with other models

Clinical Benchmarks Index
60.6rank 42 of 148; 74.3 × 0.816 = 60.6, from 2 of 10 boards
Boards
2 of 13
Results
2
Latest measurement
Sep 2026

Results

Each line is placed on its own board. Dark tick: the board leader.

Documentation and coding

  1. MedScribe (Vals AI)
    model ID grok/grok-4.5; temperature=1; top_p=0.95; max_output_tokens=30000; reasoning_effort=high
    86.88
    Rank 16 of 105Leader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  2. MedCode (Vals AI)
    model ID grok/grok-4.5; reasoning_effort=high; temperature=1; top_p=0.95; max_output_tokens=30000
    43.29
    Rank 43 of 103Leader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026

Sources

Open a line for the quote and page.

  1. 16MedScribe (Vals AI) model ID grok/grok-4.5; temperature=1; top_p=0.95; max_output_tokens=30000; rea… 86.88
    Printed as 86.88%Official leaderboard, measured Sep 2026Configuration: model ID grok/grok-4.5; temperature=1; top_p=0.95; max_output_tokens=30000; reasoning_effort=high
    Vals AI MedScribe leaderboard official leaderboard, Vals AI, 3 Sep 2026. Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 16 of 105 (Grok 4.5), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["grok/grok-4.5"].
    16 | Grok 4.5 | 86.88%±1.94 | $2/$6 | 11m45s
    Every result from this document
  2. 43MedCode (Vals AI) model ID grok/grok-4.5; reasoning_effort=high; temperature=1; top_p=0.95; max_o… 43.29
    Printed as 43.29%Official leaderboard, measured Sep 2026Configuration: model ID grok/grok-4.5; reasoning_effort=high; temperature=1; top_p=0.95; max_output_tokens=30000
    Vals AI MedCode leaderboard official leaderboard, Vals AI, 29 Sep 2026. MedCode leaderboard, Overall task, All Models expanded, rank 43 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["grok/grok-4.5"].
    43 | Grok 4.5 | 43.29%±2.31 | $2/$6 | 59.64s
    Every result from this document

Other SpaceX AI models: Grok 4, Grok 4.1 Fast Non-Reasoning, Grok 4.1 Fast (Reasoning), Grok 4.20, Grok 4.3, Grok 4.6, Grok 4.7, Grok 4 Fast (Non-Reasoning), Grok 4 Fast (Reasoning)