ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Command A+vsPhi-4 Reasoning

Command A+ leads 1 of 1 shared benchmark. Command A+ has the larger context window (128K tokens).

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

Shared benchmarks
1 – 0
Command A+ leads
Cheaper per token
list price, input + output
Larger context
Command A+
128K tokens
Provider uptime (30d)
100% · —
Cohere · Microsoft
Command A+
Cohere · released 2026-05-20
textvision
Context
128K
Max out
64K
Input /1M
Output /1M
Cached /1M
Scores
9 · 1 core
Phi-4 Reasoning
Microsoft · released 2025-04-30
text
Context
33K
Max out
33K
Input /1M
Output /1M
Cached /1M
Scores
4 · 4 core
Quality

Benchmark matrix

BenchmarkCommand A+Phi-4 ReasoningΔEdge
Reported by both · 1
AIME 202590% 62.9% +27.1 ptCommand A+
Only Command A+ reports · 8
CharXiv Reasoning52.7% not reported
IFBench74% not reported
MathVista80.6% not reported
MMMU75.1% not reported
MMMU-Pro63% not reported
SciCode38% not reported
Tau2-bench Telecom85% not reported
Terminal-Bench Hard25% not reported
Only Phi-4 Reasoning reports · 3
GPQA Diamondnot reported65.8%
MMLU-Pronot reported74.3%
HumanEval+not reported92.9%
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 Command A+ minus Phi-4 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

SpecCommand A+Phi-4 ReasoningEdge
Context window128K tokens33K tokensCommand A+
Max output64K tokens33K tokensCommand A+
Input price / 1M
Output price / 1M
Cached input / 1M
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
Modalitiestext · visiontextCommand A+
Released2026-05-202025-04-30
Cited benchmark scores94
Reliability

Provider status

All providers
Built by Respan
Which one wins on your data?

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