ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Haiku 4.5vsQwen3.5-Flash

Qwen3.5-Flash leads 3 of 3 shared benchmarks. Qwen3.5-Flash is 19x cheaper per token. Qwen3.5-Flash has the larger context window (1M tokens).

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

Shared benchmarks
0 – 3
Qwen3.5-Flash leads
Cheaper per token
Qwen3.5-Flash
19x cheaper, input + output
Larger context
Qwen3.5-Flash
1M tokens
Provider uptime (30d)
100% · —
Anthropic · Qwen
Claude Haiku 4.5
Anthropic · released 2025-10-15
textvision
Context
200K
Max out
64K
Input /1M
$1
Output /1M
$5
Cached /1M
$0.1
Scores
4 · 4 core
Qwen3.5-Flash
Qwen · released 2026-02-23
textvision
Context
1M
Max out
Input /1M
$0.029
Output /1M
$0.287
Cached /1M
Scores
5 · 5 core
Quality

Benchmark matrix

BenchmarkClaude Haiku 4.5Qwen3.5-FlashΔEdge
Reported by both · 3
GPQA Diamond71.2% epoch82.3% epoch-11.1 ptQwen3.5-Flash
OTIS Mock AIME 2024-2025 (Epoch AI run)66.7% epoch84.4% epoch-17.7 ptQwen3.5-Flash
SimpleQA Verified13.2% epoch20.3% epoch-7.1 ptQwen3.5-Flash
Only Claude Haiku 4.5 reports · 1
SWE-bench Verified73.3% not reported
Only Qwen3.5-Flash reports · 2
LMArena Elonot reported1397.7
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported9.5% 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 Haiku 4.5 minus Qwen3.5-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 Haiku 4.5Qwen3.5-FlashEdge
Context window200K tokens1M tokensQwen3.5-Flash
Max output64K tokens
Input price / 1M$1 $0.029 Qwen3.5-Flash
Output price / 1M$5 $0.287 Qwen3.5-Flash
Cached input / 1M$0.1
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$6$0.316Qwen3.5-Flash
Modalitiestext · visiontext · visionTie
Released2025-10-152026-02-23
Cited benchmark scores45
Reliability

Provider status

All providers
More matchups

Claude Haiku 4.5 vs …

More matchups

Qwen3.5-Flash vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude Haiku 4.5 and Qwen3.5-Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.