ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Opus 4.8vsKimi K2.6

Claude Opus 4.8 leads 6 of 7 shared benchmarks. Claude Opus 4.8 has the larger context window (1M tokens).

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

Shared benchmarks
6 – 1
Claude Opus 4.8 leads
Cheaper per token
list price, input + output
Larger context
Claude Opus 4.8
1M tokens
Provider uptime (30d)
100% · 100%
Anthropic · Moonshot AI
Claude Opus 4.8
Anthropic · released 2026-05-28
textvision
Context
1M
Max out
128K
Input /1M
$5
Output /1M
$25
Cached /1M
$0.5
Scores
17 · 13 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 4.8Kimi K2.6ΔEdge
Reported by both · 7
GPQA Diamond93.6% 90.8% epoch+2.8 ptClaude Opus 4.8
AIME 2026100% matharena95.8% matharena+4.2 ptClaude Opus 4.8
LMArena Elo1452.7 1454.9 -2.2Kimi K2.6
FrontierMath Tier 4 v2 (Epoch AI run)56.1% epoch25.6% epoch+30.5 ptClaude Opus 4.8
FrontierMath Tiers 1-3 v2 (Epoch AI run)80% epoch57.2% epoch+22.8 ptClaude Opus 4.8
OTIS Mock AIME 2024-2025 (Epoch AI run)98.3% epoch96.1% epoch+2.2 ptClaude Opus 4.8
SimpleQA Verified53% epoch34.9% epoch+18.1 ptClaude Opus 4.8
Only Claude Opus 4.8 reports · 9
SWE-bench Verified88.6% not reported
Humanity's Last Exam (no tools)49.8% not reported
BrowseComp84.3% not reported
Humanity's Last Exam (with tools)57.9% not reported
OSWorld-Verified83.4% not reported
SWE-bench Multilingual84.4% not reported
SWE-bench Multimodal38.4% not reported
SWE-Bench Pro69.2% not reported
Terminal-Bench 2.174.6% not reported
Only Kimi K2.6 reports · 7
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%
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 Claude Opus 4.8 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 4.8Kimi K2.6Edge
Context window1M tokens256K tokensClaude Opus 4.8
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
Released2026-05-282026-04-20
Cited benchmark scores1714
Reliability

Provider status

All providers
More matchups

Claude Opus 4.8 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 4.8 and Kimi K2.6 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.