ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Sonnet 4.5vsStep 3.5 Flash

Claude Sonnet 4.5 and Step 3.5 Flash split their 3 shared benchmarks evenly. Step 3.5 Flash has the larger context window (256K tokens).

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

Shared benchmarks
1 – 1
even split
Cheaper per token
list price, input + output
Larger context
Step 3.5 Flash
256K tokens
Provider uptime (30d)
100% · —
Anthropic · StepFun
Claude Sonnet 4.5
Anthropic · released 2025-09-29
textvision
Context
200K
Max out
64K
Input /1M
$3
Output /1M
$15
Cached /1M
$0.3
Scores
21 · 10 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 Sonnet 4.5Step 3.5 FlashΔEdge
Reported by both · 3
SWE-bench Verified77.2% 74.4% +2.8 ptClaude Sonnet 4.5
AIME 202584.2% matharena97.3% -13.1 ptStep 3.5 Flash
Terminal-Bench 2.051% 51% 0Tie
Only Claude Sonnet 4.5 reports · 17
GPQA Diamond83.4% not reported
Humanity's Last Exam (no tools)17.7% not reported
ARC-AGI-2 (Verified)13.6% not reported
FrontierMath Tier 4 v2 (Epoch AI run)2.4% epochnot reported
FrontierMath Tiers 1-3 v2 (Epoch AI run)23.9% epochnot reported
GDPval-AA1276 not reported
Humanity's Last Exam (with tools)33.6% not reported
MCP Atlas43.8% not reported
MMMLU89.5% not reported
MMMU-Pro (no tools)63.4% not reported
MMMU-Pro (with tools)68.9% not reported
OSWorld-Verified61.4% not reported
OTIS Mock AIME 2024-2025 (Epoch AI run)77.8% epochnot reported
SimpleQA Verified30.7% epochnot reported
SWE-bench Verified (Epoch AI run)71.3% epochnot reported
Tau2-bench Retail86.2% not reported
Tau2-bench Telecom98% not reported
Only Step 3.5 Flash reports · 14
AIME 2026not reported96.7% matharena
LMArena Elonot reported1403.7
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 Sonnet 4.5 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 Sonnet 4.5Step 3.5 FlashEdge
Context window200K tokens256K tokensStep 3.5 Flash
Max output64K tokens
Input price / 1M$3
Output price / 1M$15
Cached input / 1M$0.3
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$18
Modalitiestext · visiontextClaude Sonnet 4.5
Released2025-09-292026-02-12
Cited benchmark scores2118
Reliability

Provider status

All providers
More matchups

Claude Sonnet 4.5 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 Sonnet 4.5 and Step 3.5 Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.