Minimax M2.1 PreviewvsPhi 3 Small 8k Instruct
Minimax M2.1 Preview leads the overall Podium Score by 10.0 points (69.0 vs 59.0).Category wins: Minimax M2.1 Preview 0 — 0 Phi 3 Small 8k Instruct.Minimax M2.1 Preview is the cheaper pick ($3/M vs $3/M per 1M output tokens). Minimax M2.1 Preview is faster (50 t/s vs 50 t/s).
Key VerdictAggregated 2026 Benchmark Analysis
Minimax M2.1 Preview is rated higher overall with a Podium Score of 69.0 (vs 59.0 for Phi 3 Small 8k Instruct). Both models show closely matched capabilities across domain benchmarks.
Coding & Engineering
Comparable
Inference Speed
Minimax M2.1 Preview (50 t/s)
Cost Efficiency
Minimax M2.1 Preview ($3/M/M)
| Metric | Minimax M2.1 Preview | Phi 3 Small 8k Instruct |
|---|---|---|
| Podium Score | 69.0 ▲ | 59.0 |
| Arena Elo | — | — |
| Intelligence Index | — | — |
| Coding | — | — |
| Math | — | — |
| Reasoning | — | — |
| Agentic | — | — |
| Knowledge | — | — |
| Multimodal | — | — |
| Long-context | — | — |
| Output speed | 50 t/s | 50 t/s |
| Output price | $3/M | $3/M |
| Context window | 128K | 128K |
Scores aggregated from five independent leaderboards. See Methodology. More head-to-heads: Minimax M2.1 vs Claude Mythos · Minimax M2.1 vs Claude Fable 5 · Minimax M2.1 vs Kimi K3 · Minimax M2.1 vs Claude Opus 5