ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

MiniMax M3vsPhi-4 Mini Reasoning

MiniMax M3 leads 1 of 1 shared benchmark. MiniMax M3 has the larger context window (1M tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
1 – 0
MiniMax M3 leads
Cheaper per token
list price, input + output
Larger context
MiniMax M3
1M tokens
Provider uptime (30d)
100% · —
MiniMax · Microsoft
MiniMax M3
MiniMax · released 2026-06-01
textvision
Context
1M
Max out
Input /1M
$0.3
Output /1M
$1.2
Cached /1M
$0.06
Scores
3 · 3 core
Phi-4 Mini Reasoning
Microsoft · released 2025-04-30
text
Context
128K
Max out
128K
Input /1M
Output /1M
Cached /1M
Scores
3 · 2 core
Quality

Benchmark matrix

BenchmarkMiniMax M3Phi-4 Mini ReasoningΔEdge
Reported by both · 1
GPQA Diamond90.9% epoch52% +38.9 ptMiniMax M3
Only MiniMax M3 reports · 2
LMArena Elo1433.5 not reported
OTIS Mock AIME 2024-2025 (Epoch AI run)71.1% epochnot reported
Only Phi-4 Mini Reasoning reports · 2
AIME 2024not reported57.5%
MATH-500not reported94.6%
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is MiniMax M3 minus Phi-4 Mini Reasoning in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecMiniMax M3Phi-4 Mini ReasoningEdge
Context window1M tokens128K tokensMiniMax M3
Max output128K tokens
Input price / 1M$0.3
Output price / 1M$1.2
Cached input / 1M$0.06
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$1.5
Modalitiestext · visiontextMiniMax M3
Released2026-06-012025-04-30
Cited benchmark scores33
Reliability

Provider status

All providers
More matchups

MiniMax M3 vs …

More matchups

Phi-4 Mini Reasoning vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run MiniMax M3 and Phi-4 Mini Reasoning on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.