Compare / Phi 4 vs MiniMax M2.1
Phi 4 vs MiniMax M2.1
Which is cheaper, which is more capable, and which does better at each kind of work, from 12 results on 3 sources that measured both models.
Phi 4 or MiniMax M2.1? The short answer
- Phi 4 is cheaper: $0.088 against $0.52 per million tokens, 6.0 times less.
- MiniMax M2.1 scores higher on the Artificial Analysis Intelligence Index: 20.9 against 5.9.
- On our business benchmarks, Phi 4 ranks higher for agents and tool use and sticking to the facts.
- On our business benchmarks, MiniMax M2.1 ranks higher for reasoning and knowledge and writing.
At a glance
| Phi 4 | MiniMax M2.1 | |
|---|---|---|
| Price per million tokens | $0.070 in · $0.14 out | $0.30 in · $1.20 out |
| Blended (3 in : 1 out) | $0.088 | $0.52 |
| Cheapest host, blended | – | $0.52 (Novita, FP8) |
| Intelligence Index | 5.9 | 20.9 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | 42 | – |
| Context window | 16,384 tokens | 204,800 tokens |
| Weights | Open | Open |
| Developer based in | the US | China |
Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.
Which is better for what
Each model's rank among models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.
| Use case | Phi 4 | MiniMax M2.1 |
|---|---|---|
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 122 of 161 | 125 of 161 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 178 of 195 | 86 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 175 of 187 | 106 of 187 |
| Sticking to the factsSummarising without inventing things, and factual answers | 3 of 153 | 116 of 153 |
Every shared result
| Benchmark | Metric | Phi 4 | MiniMax M2.1 |
|---|---|---|---|
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 5.90 | 20.9 |
| Artificial Analysisreported | GPQA Diamond% of questions | 57.5% | 83.0% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 3.8% | 23.2% |
| Artificial Analysisreported | IFBench% of instructions | 23.5% | 69.9% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 0.0% | 67.7% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 3.8% | 28.8% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 0.0% | 85.4% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 19.0% | 31.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.34 | 0.41 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 25.7 | 41.6 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 80.7% | 98.5% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 3.7% | 11.8% |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.
Quick answers
Is Phi 4 better than MiniMax M2.1?
It depends on the task. Among models available today, on our benchmarks and licensed sources, Phi 4 ranks higher for agents and tool use and sticking to the facts; MiniMax M2.1 ranks higher for reasoning and knowledge and writing.
Which is cheaper, Phi 4 or MiniMax M2.1?
Phi 4 costs $0.088 per million tokens (three input to one output), against $0.52 for MiniMax M2.1.
Run Phi 4 and MiniMax M2.1 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.