ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Opus 4.6vsStep 3.5 Flash

Claude Opus 4.6 leads 3 of 4 shared benchmarks. 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
3 – 0
Claude Opus 4.6 leads · 1 tied
Cheaper per token
list price, input + output
Larger context
Claude Opus 4.6
1M tokens
Provider uptime (30d)
100% · —
Anthropic · StepFun
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
Step 3.5 Flash
StepFun · released 2026-02-12
text
Context
256K
Max out
Input /1M
Output /1M
Cached /1M
Scores
18 · 5 core
Quality

Benchmark matrix

BenchmarkClaude Opus 4.6Step 3.5 FlashΔEdge
Reported by both · 4
SWE-bench Verified80.8% 74.4% +6.4 ptClaude Opus 4.6
AIME 202696.7% matharena96.7% matharena0Tie
LMArena Elo1497.5 1403.7 +93.8Claude Opus 4.6
Terminal-Bench 2.065.4% 51% +14.4 ptClaude Opus 4.6
Only Claude Opus 4.6 reports · 14
GPQA Diamond91.3% not reported
ARC-AGI-2 (Verified)68.8% not reported
FrontierMath Tier 4 v2 (Epoch AI run)26.8% epochnot reported
FrontierMath Tiers 1-3 v2 (Epoch AI run)66% 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
OTIS Mock AIME 2024-2025 (Epoch AI run)94.4% epochnot reported
SimpleQA Verified47% epochnot reported
SWE-bench Verified (Epoch AI run)78.7% epochnot reported
Tau2-bench Retail91.9% not reported
Tau2-bench Telecom99.3% not reported
Only Step 3.5 Flash reports · 13
AIME 2025not reported97.3%
BrowseCompnot reported51.6%
BrowseComp (with context manager)not reported69%
BrowseComp-ZHnot reported66.9%
BrowseComp-ZH (with context manager)not reported73.7%
GAIA (no file)not reported84.5%
HMMT 2025 (Feb/Nov average)not reported96.2%
IMOAnswerBenchnot reported85.4%
LiveCodeBench v6not reported86.4%
ResearchRubricsnot reported65.3%
Tau2-Benchnot reported88.2%
xbench-DeepSearch 2025.05not reported83.7%
xbench-DeepSearch 2025.10not reported56.3%
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 4.6 minus Step 3.5 Flash 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 4.6Step 3.5 FlashEdge
Context window1M tokens256K tokensClaude Opus 4.6
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 · visiontextClaude Opus 4.6
Released2026-02-052026-02-12
Cited benchmark scores1918
Reliability

Provider status

All providers
More matchups

Claude Opus 4.6 vs …

More matchups

Step 3.5 Flash vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude Opus 4.6 and Step 3.5 Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.