Model comparison

Phi-4 Mini vs Qwen3 Max

Qwen3 Max is the stronger model overall, scoring 43.7 to 30.9 on the Noometry Index. Phi-4 Mini costs 18× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.

Last verified October 10, 2026. 0 shared benchmarks.

Phi-4 Mini

Microsoft

30.9

Rank #283 Reported

Qwen3 Max

Alibaba (Qwen)

43.7

Rank #87 Confirmed

Summary

The widest gap is in knowledge, where Qwen3 Max leads 48.1 to 25.3.
Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
Qwen3 Max accepts more context: 262K tokens versus 128K.
Phi-4 Mini has downloadable open weights; the other is API-only.

Side by side

Phi-4 Mini and Qwen3 Max specifications
	Phi-4 Mini	Qwen3 Max
Provider	Microsoft	Alibaba (Qwen)
Noometry Index	30.9	43.7
Released	2024-12-11	2025-09-23
Weights	Open	Proprietary
Context window	128K	262K
Max output	4K	66K
Input $ / M tokens	$0.075	$1.20
Output $ / M tokens	$0.30	$6
Results tracked	3	33

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Qwen3 Max leads

Phi-4 Mini: 28.1 (#317), Qwen3 Max: 43.0 (#93)

Coding benchmarks
Benchmark	Phi-4 Mini	Qwen3 Max
SciCode	10.8%	—
LMArena Coding	—	1456
ALE-Bench	—	370.45

Agentic & Tool Use Not comparable

Phi-4 Mini: —, Qwen3 Max: —

Agentic & Tool Use benchmarks
Benchmark	Phi-4 Mini	Qwen3 Max
Vending-Bench 2	—	71.56

Reasoning Too close to call

Phi-4 Mini: 22.4 (#195), Qwen3 Max: 22.6 (#190)

Reasoning benchmarks
Benchmark	Phi-4 Mini	Qwen3 Max
Kagi LLM Benchmark	—	72.5%
NYT Connections (extended)	—	30.1%
CritPt	0%	—
Chess Puzzles	—	4%
LMArena Hard Prompts	—	1448
Mystery Game Puzzles	—	5%
DTBench	—	82.1%
LMCA	—	28.3%
Epoch Capabilities Index	—	142.38

Math Not comparable

Phi-4 Mini: —, Qwen3 Max: 38.7 (#131)

Math benchmarks
Benchmark	Phi-4 Mini	Qwen3 Max
FrontierMath (Tiers 1-3)	—	18.9%
OTIS Mock AIME 2024-2025	—	73.3%
LMArena Math	—	1446
MATH Level 5	—	97.1%

Knowledge Qwen3 Max leads

Phi-4 Mini: 25.3 (#262), Qwen3 Max: 48.1 (#78)

Knowledge benchmarks
Benchmark	Phi-4 Mini	Qwen3 Max
GPQA Diamond	—	72.6%
SimpleQA Verified	—	48.7%
Vectara Hallucination Rate	23.5%	—
LMArena Expert	—	1455

Multilingual Not comparable

Phi-4 Mini: —, Qwen3 Max: 53.7 (#62)

Multilingual benchmarks
Benchmark	Phi-4 Mini	Qwen3 Max
LMArena Non-English	—	1429
LMArena Chinese	—	1478
LMArena French	—	1449
LMArena German	—	1463
LMArena Japanese	—	1397
LMArena Korean	—	1399
LMArena Russian	—	1428
LMArena Spanish	—	1462

Instruction Following Not comparable

Phi-4 Mini: —, Qwen3 Max: 74.8 (#87)

Instruction Following benchmarks
Benchmark	Phi-4 Mini	Qwen3 Max
LMArena Instruction Following	—	1419

Long Context Not comparable

Phi-4 Mini: —, Qwen3 Max: 41.6 (#134)

Long Context benchmarks
Benchmark	Phi-4 Mini	Qwen3 Max
Fiction.LiveBench	—	66.7%
CL-bench	—	14.5%
LMArena Longer Query	—	1438

Writing & Preference Not comparable

Phi-4 Mini: —, Qwen3 Max: 62.4 (#76)

Writing & Preference benchmarks
Benchmark	Phi-4 Mini	Qwen3 Max
LMArena Text	—	1439
LMArena Creative Writing	—	1402
LMArena Multi-Turn	—	1446

Frequently asked questions

Is Phi-4 Mini better than Qwen3 Max?

Which is cheaper, Phi-4 Mini or Qwen3 Max?

Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Qwen3 Max lists at $1.20 and $6.

Is Phi-4 Mini or Qwen3 Max better for coding?

Qwen3 Max scores higher on coding benchmarks: 43.0 versus 28.1 in the Noometry coding category.

Which has the bigger context window?

Qwen3 Max does, with 262K tokens against 128K.

How many benchmarks do Phi-4 Mini and Qwen3 Max share?

0 benchmarks have published results for both models. Phi-4 Mini has 3 scored results on Noometry and Qwen3 Max has 33.