Model comparison
Phi 3 Mini 4k Instruct vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 27.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 0 categories and Qwen3 235B-A22B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3 235B-A22B leads 59.6 to 27.6.
- The biggest single-benchmark swing is Chess Puzzles: 0% for Phi 3 Mini 4k Instruct and 12% for Qwen3 235B-A22B.
Side by side
| Phi 3 Mini 4k Instruct | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 27.9 | 43.5 |
| Released | 2024-04-23 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 35 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Phi 3 Mini 4k Instruct: 26.6 (#323), Qwen3 235B-A22B: 44.3 (#75)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen3 235B-A22B |
|---|---|---|
| LMArena Coding | 1093 | 1445 |
| Aider Polyglot | — | 59.6% |
| SciCode | — | 42.4% |
| WeirdML | — | 41% |
| LiveBench Coding | 15.5% | — |
| HumanEval+ | 59.1% | — |
| MBPP+ | 54.2% | — |
Agentic & Tool Use Not comparable
Phi 3 Mini 4k Instruct: —, Qwen3 235B-A22B: 33.9 (#51)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 52.1% |
| Vending-Bench 2 | — | -11.34 |
Reasoning Qwen3 235B-A22B leads
Phi 3 Mini 4k Instruct: 14.1 (#328), Qwen3 235B-A22B: 15.7 (#311)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen3 235B-A22B |
|---|---|---|
| Chess Puzzles | 0% | 12% |
| LMArena Hard Prompts | 1072 | 1433 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31% |
| Kagi LLM Benchmark | — | 69.4% |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| LiveBench Reasoning | 26.8% | — |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LiveBench Data Analysis | 34.7% | — |
| LMCA | — | 29.3% |
| Adversarial NLI | 52.8% | — |
| BIG-Bench Hard | 71.7% | — |
| Epoch Capabilities Index | — | 143.85 |
| ForecastBench | — | 59.7 |
| HellaSwag | 76.7% | — |
| LiveBench | 22.4% | — |
| WinoGrande | 70.8% | — |
Math Qwen3 235B-A22B leads
Phi 3 Mini 4k Instruct: 26.6 (#257), Qwen3 235B-A22B: 50.4 (#57)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen3 235B-A22B |
|---|---|---|
| LMArena Math | 1111 | 1432 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| Omni-MATH | — | 71.8% |
| LiveBench Math | 15.7% | — |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3 235B-A22B leads
Phi 3 Mini 4k Instruct: 28.5 (#246), Qwen3 235B-A22B: 49.6 (#73)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen3 235B-A22B |
|---|---|---|
| LMArena Expert | 1045 | 1463 |
| GPQA Diamond | — | 80.1% |
| SimpleQA Verified | — | 40.4% |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 72.7% |
| ARC (AI2) Challenge | 84.9% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 64% | — |
Multilingual Qwen3 235B-A22B leads
Phi 3 Mini 4k Instruct: 26.3 (#280), Qwen3 235B-A22B: 52.3 (#89)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1021 | 1409 |
| LMArena Chinese | 1021 | 1481 |
| LMArena French | 1076 | 1445 |
| LMArena German | 1044 | 1433 |
| LMArena Japanese | 935 | 1399 |
| LMArena Korean | 905 | 1391 |
| LMArena Russian | 1022 | 1411 |
| LMArena Spanish | 1085 | 1430 |
Instruction Following Qwen3 235B-A22B leads
Phi 3 Mini 4k Instruct: 47.7 (#303), Qwen3 235B-A22B: 72.6 (#136)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1053 | 1408 |
| LiveBench Instruction Following | 39.1% | — |
| IFEval | — | 83.5% |
Long Context Qwen3 235B-A22B leads
Phi 3 Mini 4k Instruct: 31.7 (#276), Qwen3 235B-A22B: 46.1 (#26)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1044 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference Qwen3 235B-A22B leads
Phi 3 Mini 4k Instruct: 27.6 (#300), Qwen3 235B-A22B: 59.6 (#108)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1073 | 1419 |
| LMArena Creative Writing | 1037 | 1384 |
| LMArena Multi-Turn | 1018 | 1432 |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1366 |
| WildBench | — | 86.6% |
| LiveBench Language | 9.2% | — |
Frequently asked questions
Is Phi 3 Mini 4k Instruct better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 27.9 on the Noometry Index.
Is Phi 3 Mini 4k Instruct or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 26.6 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 4k Instruct and Qwen3 235B-A22B share?
18 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Qwen3 235B-A22B has 49.