Model comparison
Phi-4 Mini vs Qwen3 8B
Qwen3 8B is the stronger model overall, scoring 33.7 to 30.9 on the Noometry Index. Phi-4 Mini costs 2.4× less per token, which makes it the better buy when Qwen3 8B's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. Phi-4 Mini scores higher in 1 category and Qwen3 8B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 8B leads 36.1 to 25.3.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 23.5% for Phi-4 Mini and 4.8% for Qwen3 8B.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $0.18 / $0.70 for Qwen3 8B.
- Qwen3 8B accepts more context: 131K tokens versus 128K.
Side by side
| Phi-4 Mini | Qwen3 8B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 30.9 | 33.7 |
| Released | 2024-12-11 | 2025-04 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 4K | 8K |
| Input $ / M tokens | $0.075 | $0.18 |
| Output $ / M tokens | $0.30 | $0.70 |
| Results tracked | 3 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 8B leads
Phi-4 Mini: 28.1 (#317), Qwen3 8B: 34.0 (#248)
| Benchmark | Phi-4 Mini | Qwen3 8B |
|---|---|---|
| SciCode | 10.8% | 22.6% |
Agentic & Tool Use Not comparable
Phi-4 Mini: —, Qwen3 8B: 30.2 (#78)
| Benchmark | Phi-4 Mini | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 42.6% |
Reasoning Phi-4 Mini leads
Phi-4 Mini: 22.4 (#195), Qwen3 8B: 16.6 (#303)
| Benchmark | Phi-4 Mini | Qwen3 8B |
|---|---|---|
| CritPt | 0% | 0% |
| Chess Puzzles | — | 5% |
| DTBench | — | 59.7% |
| LMCA | — | 8.8% |
| Epoch Capabilities Index | — | 136.17 |
Math Not comparable
Phi-4 Mini: —, Qwen3 8B: 34.9 (#191)
| Benchmark | Phi-4 Mini | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 56.1% |
Knowledge Qwen3 8B leads
Phi-4 Mini: 25.3 (#262), Qwen3 8B: 36.1 (#173)
| Benchmark | Phi-4 Mini | Qwen3 8B |
|---|---|---|
| Vectara Hallucination Rate | 23.5% | 4.8% |
| GPQA Diamond | — | 56.8% |
Long Context Not comparable
Phi-4 Mini: —, Qwen3 8B: 37.9 (#210)
| Benchmark | Phi-4 Mini | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |
Frequently asked questions
Is Phi-4 Mini better than Qwen3 8B?
Qwen3 8B is the stronger model overall, scoring 33.7 to 30.9 on the Noometry Index. Phi-4 Mini costs 2.4× less per token, which makes it the better buy when Qwen3 8B's lead doesn't matter for your workload.
Which is cheaper, Phi-4 Mini or Qwen3 8B?
Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Qwen3 8B lists at $0.18 and $0.70.
Is Phi-4 Mini or Qwen3 8B better for coding?
Qwen3 8B scores higher on coding benchmarks: 34.0 versus 28.1 in the Noometry coding category.
Which has the bigger context window?
Qwen3 8B does, with 131K tokens against 128K.
How many benchmarks do Phi-4 Mini and Qwen3 8B share?
3 benchmarks have published results for both models. Phi-4 Mini has 3 scored results on Noometry and Qwen3 8B has 11.