Model comparison
Phi-4 vs Qwen3 Coder Next
Qwen3 Coder Next is the stronger model overall, scoring 33.8 to 30.9 on the Noometry Index. Phi-4 costs 3.3× less per token, which makes it the better buy when Qwen3 Coder Next's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- The widest gap is in reasoning, where Qwen3 Coder Next leads 21.7 to 17.0.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.12 / $0.80 for Qwen3 Coder Next.
- Qwen3 Coder Next accepts more context: 262K tokens versus 128K.
Side by side
| Phi-4 | Qwen3 Coder Next | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 30.9 | 33.8 |
| Released | 2024-12-11 | 2026-02-02 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 66K |
| Input $ / M tokens | $0.07 | $0.12 |
| Output $ / M tokens | $0.14 | $0.80 |
| Results tracked | 37 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 Coder Next leads
Phi-4: 33.8 (#237), Qwen3 Coder Next: 35.8 (#206)
| Benchmark | Phi-4 | Qwen3 Coder Next |
|---|---|---|
| SciCode | — | 32.3% |
| WeirdML | — | 34.4% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 30.7% | — |
| LMArena Coding | 1231 | — |
| BigCodeBench Complete | 55.4% | — |
Agentic & Tool Use Not comparable
Phi-4: 22.6 (#120), Qwen3 Coder Next: —
| Benchmark | Phi-4 | Qwen3 Coder Next |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.8% | — |
| BALROG | 11.6% | — |
Reasoning Qwen3 Coder Next leads
Phi-4: 17.0 (#287), Qwen3 Coder Next: 21.7 (#191)
| Benchmark | Phi-4 | Qwen3 Coder Next |
|---|---|---|
| CritPt | — | 0% |
| Chess Puzzles | 1% | — |
| LiveBench Reasoning | 47.8% | — |
| LMArena Hard Prompts | 1220 | — |
| LiveBench Data Analysis | 45.2% | — |
| Epoch Capabilities Index | 130.43 | — |
| LiveBench | 41.6% | — |
Math Not comparable
Phi-4: 19.6 (#279), Qwen3 Coder Next: —
| Benchmark | Phi-4 | Qwen3 Coder Next |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 13.8% | — |
| LiveBench Math | 42% | — |
| LMArena Math | 1246 | — |
| MATH Level 5 | 64.9% | — |
Knowledge Not comparable
Phi-4: 32.5 (#204), Qwen3 Coder Next: —
| Benchmark | Phi-4 | Qwen3 Coder Next |
|---|---|---|
| GPQA Diamond | 56.1% | — |
| Confabulations | 29.4% | — |
| Vectara Hallucination Rate | 3.7% | — |
| LMArena Expert | 1203 | — |
| MMLU | 84.8% | — |
Multilingual Not comparable
Phi-4: 37.4 (#232), Qwen3 Coder Next: —
| Benchmark | Phi-4 | Qwen3 Coder Next |
|---|---|---|
| LMArena Non-English | 1197 | — |
| LMArena Chinese | 1211 | — |
| LMArena French | 1223 | — |
| LMArena German | 1222 | — |
| LMArena Japanese | 1158 | — |
| LMArena Korean | 1151 | — |
| LMArena Russian | 1209 | — |
| LMArena Spanish | 1234 | — |
Instruction Following Not comparable
Phi-4: 60.6 (#246), Qwen3 Coder Next: —
| Benchmark | Phi-4 | Qwen3 Coder Next |
|---|---|---|
| LiveBench Instruction Following | 58.4% | — |
| LMArena Instruction Following | 1201 | — |
Long Context Not comparable
Phi-4: 36.9 (#221), Qwen3 Coder Next: —
| Benchmark | Phi-4 | Qwen3 Coder Next |
|---|---|---|
| LMArena Longer Query | 1217 | — |
Writing & Preference Not comparable
Phi-4: 40.7 (#239), Qwen3 Coder Next: —
| Benchmark | Phi-4 | Qwen3 Coder Next |
|---|---|---|
| LMArena Text | 1217 | — |
| LMArena Creative Writing | 1182 | — |
| Short-Story Creative Writing | 62.6% | — |
| LMArena Multi-Turn | 1206 | — |
| LiveBench Language | 25.6% | — |
Frequently asked questions
Is Phi-4 better than Qwen3 Coder Next?
Qwen3 Coder Next is the stronger model overall, scoring 33.8 to 30.9 on the Noometry Index. Phi-4 costs 3.3× less per token, which makes it the better buy when Qwen3 Coder Next's lead doesn't matter for your workload.
Which is cheaper, Phi-4 or Qwen3 Coder Next?
Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Qwen3 Coder Next lists at $0.12 and $0.80.
Is Phi-4 or Qwen3 Coder Next better for coding?
Qwen3 Coder Next scores higher on coding benchmarks: 35.8 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3 Coder Next does, with 262K tokens against 128K.
How many benchmarks do Phi-4 and Qwen3 Coder Next share?
0 benchmarks have published results for both models. Phi-4 has 37 scored results on Noometry and Qwen3 Coder Next has 3.