MDL
GPT-5.1
OpenAI
Verified against Artificial Analysis · Jul 13, 2026
Capability
92
percentile index
Price /M
$1.25 / $10
in / out
Context
400K
tokens
Avg score
70.0
10 benchmarks
AA Intelligence
36.9
index
Speed
114 tok/s
TTFT 32s
Released
Nov 13, 2025
About
GPT-5.1 is a proprietary model in the GPT family from OpenAI. Benchmarked on 10 evals, averaging 70.0.
Benchmark scores · 10
avg 70.0 — higher is betterThe research behind this model
all papers mentioning it →FinGuard: Detecting Financial Regulatory Non-Compliance in LLM InteractionsMay 28, 2026Evaluating Large Language Models as Live Strategic Agents: Provider Performance, Hybrid Decomposition, and Operational Gaps in Timed Risk PlayMay 21, 2026Can Large Language Models Reliably Correct Errors in Low-Resource ASR? A Contamination-Aware Case Study on West FrisianMay 19, 2026ContractBench: Can LLM Agents Preserve Observation Contracts?May 17, 2026HLS-Seek: QoR-Aware Code Generation for High-Level Synthesis via Proxy Comparative Reward Reinforcement LearningMay 13, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Output speed114 tok/s
Latency (TTFT)32s
Price in / out$1.25 / $10 per 1M
Blended price$3.44 / 1M
Coding index49.4
Math index94.0
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$10/M