ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

GPT-5.1vsPhi-4 Reasoning

GPT-5.1 leads 2 of 2 shared benchmarks. GPT-5.1 has the larger context window (400K tokens).

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

Shared benchmarks
2 – 0
GPT-5.1 leads
Cheaper per token
list price, input + output
Larger context
GPT-5.1
400K tokens
Provider uptime (30d)
94.2446% · —
OpenAI · Microsoft
GPT-5.1
OpenAI · released 2025-11-13
textvision
Context
400K
Max out
128K
Input /1M
$1.25
Output /1M
$10
Cached /1M
$0.125
Scores
6 · 6 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

BenchmarkGPT-5.1Phi-4 ReasoningΔEdge
Reported by both · 2
GPQA Diamond87.6% epoch65.8% +21.8 ptGPT-5.1
AIME 202594.2% matharena62.9% +31.3 ptGPT-5.1
Only GPT-5.1 reports · 4
LMArena Elo1422.6 not reported
OTIS Mock AIME 2024-2025 (Epoch AI run)88.6% epochnot reported
SimpleQA Verified48% epochnot reported
SWE-bench Verified (Epoch AI run)68% epochnot reported
Only Phi-4 Reasoning reports · 2
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 GPT-5.1 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

SpecGPT-5.1Phi-4 ReasoningEdge
Context window400K tokens33K tokensGPT-5.1
Max output128K tokens33K tokensGPT-5.1
Input price / 1M$1.25
Output price / 1M$10
Cached input / 1M$0.125
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$11.25
Modalitiestext · visiontextGPT-5.1
Released2025-11-132025-04-30
Cited benchmark scores64
Reliability

Provider status

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

Public benchmarks are a starting point. Run GPT-5.1 and Phi-4 Reasoning on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.