ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Gemini 2.5 ProvsKimi K2.6

Kimi K2.6 leads 5 of 6 shared benchmarks. Gemini 2.5 Pro has the larger context window (1.0M tokens).

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

Shared benchmarks
1 – 5
Kimi K2.6 leads
Cheaper per token
list price, input + output
Larger context
Gemini 2.5 Pro
1.0M tokens
Provider uptime (30d)
100% · 100%
Google · Moonshot AI
Gemini 2.5 Pro
Google · released 2025-06-17
textvisionaudio
Context
1.0M
Max out
66K
Input /1M
$1.25
Output /1M
$10
Cached /1M
$0.125
Scores
14 · 9 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

BenchmarkGemini 2.5 ProKimi K2.6ΔEdge
Reported by both · 6
GPQA Diamond86.4% 90.8% epoch-4.4 ptKimi K2.6
LMArena Elo1457.8 1454.9 +2.9Gemini 2.5 Pro
FrontierMath Tier 4 v2 (Epoch AI run)0% epoch25.6% epoch-25.6 ptKimi K2.6
FrontierMath Tiers 1-3 v2 (Epoch AI run)24.6% epoch57.2% epoch-32.6 ptKimi K2.6
OTIS Mock AIME 2024-2025 (Epoch AI run)84.7% epoch96.1% epoch-11.4 ptKimi K2.6
SWE-bench Verified (Epoch AI run)57.6% epoch76.7% epoch-19.1 ptKimi K2.6
Only Gemini 2.5 Pro reports · 6
SWE-bench Verified59.6% not reported
AIME 202588% not reported
Humanity's Last Exam (no tools)21.6% not reported
Aider Polyglot82.2% not reported
LiveCodeBench74.2% not reported
MMMU82% not reported
Only Kimi K2.6 reports · 8
AIME 2026not reported95.8% matharena
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%
ProgramBenchnot reported48.3%
SimpleQA Verifiednot reported34.9% 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 Gemini 2.5 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

SpecGemini 2.5 ProKimi K2.6Edge
Context window1.0M tokens256K tokensGemini 2.5 Pro
Max output66K tokens
Input price / 1M$1.25
Output price / 1M$10
Cached input / 1M$0.125
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$11.25
Modalitiestext · vision · audiotext · visionGemini 2.5 Pro
Released2025-06-172026-04-20
Cited benchmark scores1414
Reliability

Provider status

All providers
More matchups

Gemini 2.5 Pro vs …

More matchups

Kimi K2.6 vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Gemini 2.5 Pro and Kimi K2.6 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.