ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

GPT-5.2 ProvsKimi K2.6

GPT-5.2 Pro leads 3 of 3 shared benchmarks. GPT-5.2 Pro has the larger context window (400K tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
3 – 0
GPT-5.2 Pro leads
Cheaper per token
list price, input + output
Larger context
GPT-5.2 Pro
400K tokens
Provider uptime (30d)
94.2446% · 100%
OpenAI · Moonshot AI
GPT-5.2 Pro
OpenAI · released 2025-12-11
textvision
Context
400K
Max out
128K
Input /1M
$21
Output /1M
$168
Cached /1M
Scores
10 · 6 core
Kimi K2.6
Moonshot AI · released 2026-04-20
textvision
Context
256K
Max out
Input /1M
Output /1M
Cached /1M
Scores
14 · 8 core
Quality

Benchmark matrix

BenchmarkGPT-5.2 ProKimi K2.6ΔEdge
Reported by both · 3
GPQA Diamond93.2% 90.8% epoch+2.4 ptGPT-5.2 Pro
FrontierMath Tier 4 v2 (Epoch AI run)46% epoch25.6% epoch+20.4 ptGPT-5.2 Pro
FrontierMath Tiers 1-3 v2 (Epoch AI run)74% epoch57.2% epoch+16.8 ptGPT-5.2 Pro
Only GPT-5.2 Pro reports · 7
AIME 2025100% not reported
Humanity's Last Exam (no tools)36.6% not reported
ARC-AGI-1 (Verified)90.5% not reported
ARC-AGI-2 (Verified)54.2% not reported
BrowseComp77.9% not reported
GDPval (wins or ties)74.1% not reported
Humanity's Last Exam (with tools)50% not reported
Only Kimi K2.6 reports · 11
AIME 2026not reported95.8% matharena
LMArena Elonot reported1454.9
Kimi Claw 24/7 Benchnot reported42.9%
Kimi Code Bench v2not reported50.9%
MCP-Atlasnot reported69.4%
MCPMark-Verifiednot reported72.8%
MLS-Bench-Litenot reported26.7%
OTIS Mock AIME 2024-2025 (Epoch AI run)not reported96.1% epoch
ProgramBenchnot reported48.3%
SimpleQA Verifiednot reported34.9% epoch
SWE-bench Verified (Epoch AI run)not reported76.7% epoch
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is GPT-5.2 Pro minus Kimi K2.6 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecGPT-5.2 ProKimi K2.6Edge
Context window400K tokens256K tokensGPT-5.2 Pro
Max output128K tokens
Input price / 1M$21
Output price / 1M$168
Cached input / 1M
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$189
Modalitiestext · visiontext · visionTie
Released2025-12-112026-04-20
Cited benchmark scores1014
Reliability

Provider status

All providers
More matchups

GPT-5.2 Pro vs …

More matchups

Kimi K2.6 vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run GPT-5.2 Pro and Kimi K2.6 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.