GPT-5 (medium)
OpenAIGPTProprietary
Description
GPT-5 Medium balances reasoning depth with response speed, providing medium-effort thinking for moderately complex tasks. Optimized for coding and agentic tasks, this variant offers more thorough analysis than instant responses while maintaining faster performance than high-effort reasoning.
Release Date
2025-08-07
Parameters
—
Context Length
400K
Modalities
file, image, text
Capability Radar
53
general
50
coding
92
reasoning
57
scienceest.
0
agents
85
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 46 | 74.0 | AA |
| General Ranking | 41 | 80.0 | AA |
| Math Reasoning | 16 | 95.0 | AA |
| Science | 54 | 70.0 | AA |
Benchmark Scores (LLM Stats)
Biology
GPQA
88.1%SR
Math
AIME 2025
88.9%SR
AA Evaluation Indices
Math Index91.7
Intelligence Index42.0
Coding Index39.0
Math 5001.0
Aime0.9
Aime 250.9
Mmlu Pro0.9
Tau20.9
Gpqa0.8
Lcr0.7
Ifbench0.7
Livecodebench0.7
Scicode0.4
Terminalbench Hard0.4
Hle0.2
LLM Stats Category Scores
Biology90
Chemistry90
General90
Math90
Physics90
Reasoning90
Pricing
Input Price$1.25 / 1M tokens
Output Price$10 / 1M tokens
Blended Price (3:1)$3.438 / 1M tokens
Speed
Tokens/sec69.5 tokens/s
Time to First Token50.11s
Time to Answer50.11s
Available Providers
(LS internal units)| Provider | Input Price | Output Price |
|---|---|---|
| OpenAI | 1.3M | 10.0M |