ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Opus 4.7vsKimi K2.6

Claude Opus 4.7 leads 7 of 8 shared benchmarks. Claude Opus 4.7 has the larger context window (1M tokens).

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

Shared benchmarks
7 – 0
Claude Opus 4.7 leads · 1 tied
Cheaper per token
list price, input + output
Larger context
Claude Opus 4.7
1M tokens
Provider uptime (30d)
100% · 100%
Anthropic · Moonshot AI
Claude Opus 4.7
Anthropic · released 2026-04-16
textvision
Context
1M
Max out
128K
Input /1M
$5
Output /1M
$25
Cached /1M
$0.5
Scores
18 · 14 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

BenchmarkClaude Opus 4.7Kimi K2.6ΔEdge
Reported by both · 8
GPQA Diamond94.2% 90.8% epoch+3.4 ptClaude Opus 4.7
AIME 202695.8% matharena95.8% matharena0Tie
LMArena Elo1483.4 1454.9 +28.5Claude Opus 4.7
FrontierMath Tier 4 v2 (Epoch AI run)31.7% epoch25.6% epoch+6.1 ptClaude Opus 4.7
FrontierMath Tiers 1-3 v2 (Epoch AI run)70.2% epoch57.2% epoch+13 ptClaude Opus 4.7
OTIS Mock AIME 2024-2025 (Epoch AI run)97.8% epoch96.1% epoch+1.7 ptClaude Opus 4.7
SimpleQA Verified51.7% epoch34.9% epoch+16.8 ptClaude Opus 4.7
SWE-bench Verified (Epoch AI run)83.5% epoch76.7% epoch+6.8 ptClaude Opus 4.7
Only Claude Opus 4.7 reports · 9
SWE-bench Verified87.6% not reported
Humanity's Last Exam (no tools)46.9% not reported
BrowseComp79.8% not reported
Humanity's Last Exam (with tools)54.7% not reported
OSWorld-Verified82.8% not reported
SWE-bench Multilingual80.5% not reported
SWE-bench Multimodal34.5% not reported
SWE-Bench Pro64.3% not reported
Terminal-Bench 2.166.1% not reported
Only Kimi K2.6 reports · 6
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%
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 Claude Opus 4.7 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

SpecClaude Opus 4.7Kimi K2.6Edge
Context window1M tokens256K tokensClaude Opus 4.7
Max output128K tokens
Input price / 1M$5
Output price / 1M$25
Cached input / 1M$0.5
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$30
Modalitiestext · visiontext · visionTie
Released2026-04-162026-04-20
Cited benchmark scores1814
Reliability

Provider status

All providers
More matchups

Claude Opus 4.7 vs …

More matchups

Kimi K2.6 vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude Opus 4.7 and Kimi K2.6 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.