ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Opus 4.6vsGPT-4o mini

Claude Opus 4.6 leads 4 of 4 shared benchmarks. GPT-4o mini is 40x cheaper per token. Claude Opus 4.6 has the larger context window (1M tokens).

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

Shared benchmarks
4 – 0
Claude Opus 4.6 leads
Cheaper per token
GPT-4o mini
40x cheaper, input + output
Larger context
Claude Opus 4.6
1M tokens
Provider uptime (30d)
100% · 94.2446%
Anthropic · OpenAI
Claude Opus 4.6
Anthropic · released 2026-02-05
textvision
Context
1M
Max out
128K
Input /1M
$5
Output /1M
$25
Cached /1M
$0.5
Scores
19 · 9 core
GPT-4o mini
OpenAI · released 2024-07-18
textvision
Context
128K
Max out
16K
Input /1M
$0.15
Output /1M
$0.6
Cached /1M
$0.075
Scores
7 · 6 core
Quality

Benchmark matrix

BenchmarkClaude Opus 4.6GPT-4o miniΔEdge
Reported by both · 4
GPQA Diamond91.3% 40.2% +51.1 ptClaude Opus 4.6
FrontierMath Tiers 1-3 v2 (Epoch AI run)66% epoch0.7% epoch+65.3 ptClaude Opus 4.6
OTIS Mock AIME 2024-2025 (Epoch AI run)94.4% epoch6.9% epoch+87.5 ptClaude Opus 4.6
SimpleQA Verified47% epoch8.3% epoch+38.7 ptClaude Opus 4.6
Only Claude Opus 4.6 reports · 14
SWE-bench Verified80.8% not reported
AIME 202696.7% matharenanot reported
LMArena Elo1497.5 not reported
ARC-AGI-2 (Verified)68.8% not reported
FrontierMath Tier 4 v2 (Epoch AI run)26.8% epochnot reported
MCP Atlas59.5% not reported
MMMLU91.1% not reported
MMMU-Pro (no tools)73.9% not reported
MMMU-Pro (with tools)77.3% not reported
OSWorld-Verified72.7% not reported
SWE-bench Verified (Epoch AI run)78.7% epochnot reported
Tau2-bench Retail91.9% not reported
Tau2-bench Telecom99.3% not reported
Terminal-Bench 2.065.4% not reported
Only GPT-4o mini reports · 2
MMLUnot reported82%
AIME 2024not reported8.6%
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 4.6 minus GPT-4o mini 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 4.6GPT-4o miniEdge
Context window1M tokens128K tokensClaude Opus 4.6
Max output128K tokens16K tokensClaude Opus 4.6
Input price / 1M$5 $0.15 GPT-4o mini
Output price / 1M$25 $0.6 GPT-4o mini
Cached input / 1M$0.5 $0.075 GPT-4o mini
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$30$0.75GPT-4o mini
Modalitiestext · visiontext · visionTie
Released2026-02-052024-07-18
Cited benchmark scores197
Reliability

Provider status

All providers
More matchups

Claude Opus 4.6 vs …

More matchups

GPT-4o mini vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude Opus 4.6 and GPT-4o mini on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.