ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Phi-4 Mini ReasoningvsQwen3 235B-A22B

Qwen3 235B-A22B leads 1 of 1 shared benchmark. Qwen3 235B-A22B has the larger context window (262K tokens).

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

Shared benchmarks
0 – 1
Qwen3 235B-A22B leads
Cheaper per token
list price, input + output
Larger context
Qwen3 235B-A22B
262K tokens
Provider uptime (30d)
— · —
Microsoft · Qwen
Phi-4 Mini Reasoning
Microsoft · released 2025-04-30
text
Context
128K
Max out
128K
Input /1M
Output /1M
Cached /1M
Scores
3 · 2 core
Qwen3 235B-A22B
Qwen · released 2025-04-29
text
Context
262K
Max out
Input /1M
Output /1M
Cached /1M
Scores
4 · 3 core
Quality

Benchmark matrix

BenchmarkPhi-4 Mini ReasoningQwen3 235B-A22BΔEdge
Reported by both · 1
GPQA Diamond52% 70.7% epoch-18.7 ptQwen3 235B-A22B
Only Phi-4 Mini Reasoning reports · 2
AIME 202457.5% not reported
MATH-50094.6% not reported
Only Qwen3 235B-A22B reports · 3
AIME 2025not reported80.8% matharena
LMArena Elonot reported1366.1
ARC-AGI-1 (pass@1)not reported40.75%
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 Phi-4 Mini Reasoning minus Qwen3 235B-A22B 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

SpecPhi-4 Mini ReasoningQwen3 235B-A22BEdge
Context window128K tokens262K tokensQwen3 235B-A22B
Max output128K tokens
Input price / 1M
Output price / 1M
Cached input / 1M
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
ModalitiestexttextTie
Released2025-04-302025-04-29
Cited benchmark scores34
Reliability

Provider status

All providers
More matchups

Phi-4 Mini Reasoning vs …

More matchups

Qwen3 235B-A22B vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Phi-4 Mini Reasoning and Qwen3 235B-A22B on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.