LIVE INTELLIGENCE · part of the Xentir AI Index

GPT-5.1 vs Kimi K2.7 Code

Name: GPT-5.1 vs Kimi K2.7 Code — benchmark results
Creator: Epoch AI
License: https://creativecommons.org/licenses/by/4.0/

GPT-5.1 · OpenAI, released 2025-11-13
Kimi K2.7 Code OPEN WEIGHTS · Moonshot, released 2026-06-12

“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-09-10 · Methodology · Data Sources

Kimi K2.7 Code leads on more of the 5 benchmarks where both are measured — GPT-5.1 on 2, Kimi K2.7 Code on 3. The remaining 4 of 9 tracked benchmarks cannot be compared: 3 have a result for only one of the two models, 1 for neither. Nothing on this page is estimated to fill those in.

Head-to-head

Measured on 5 of 9 tracked benchmarks for both models — GPT-5.1 leads on 2, Kimi K2.7 Code leads on 3.

Benchmark	GPT-5.1	Kimi K2.7 Code	Leads
Epoch Capabilities Index (ECI)	149.7	150.1	Kimi K2.7 Code
SWE-bench Verified	0.669 (high)	Not measured	Comparison unavailable — Kimi K2.7 Code has no published result
GPQA Diamond	0.876 (high)	0.879	Kimi K2.7 Code
MATH Level 5	Not measured	Not measured	Not measured on both
OTIS Mock AIME 2024-2025	0.886 (high)	0.956	Kimi K2.7 Code
FrontierMath	0.310 (high)	Not measured	Comparison unavailable — Kimi K2.7 Code has no published result
FrontierMath Tier 4	0.125 (high)	Not measured	Comparison unavailable — Kimi K2.7 Code has no published result
SimpleQA Verified	0.480 (high)	0.365	GPT-5.1
Chess Puzzles	0.320 (high)	0.210	GPT-5.1

Benchmark results measure specific tasks and should not be treated as a universal measure of model quality. A model with no row here for a benchmark has not been measured on it — that is left blank, never estimated.

What remains uncertain

Kimi K2.7 Code has no published result on FrontierMath, FrontierMath Tier 4, SWE-bench Verified.
1 tracked benchmark has no published result for either model.

A missing result means Xentir has not found one published by the source it cites, not that the model performs badly. See Data Sources.

Reference price

Per 1M tokens	GPT-5.1	Kimi K2.7 Code
Output	$10.00	—

List price as published by the vendor. Xentir does not verify negotiated or enterprise rates, and price is not a measure of capability — see Data Sources.

Full profiles

GPT-5.1 → · Kimi K2.7 Code → · the full AI Model Rankings table