ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Opus 4.7vsPhi-4

Claude Opus 4.7 leads 3 of 3 shared benchmarks. Claude Opus 4.7 has the larger context window (1M tokens).

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

Shared benchmarks
3 – 0
Claude Opus 4.7 leads
Cheaper per token
list price, input + output
Larger context
Claude Opus 4.7
1M tokens
Provider uptime (30d)
100% · —
Anthropic · Microsoft
Claude Opus 4.7
Anthropic · released 2026-04-16
textvision
Context
1M
Max out
128K
Input /1M
$5
Output /1M
$25
Cached /1M
$0.5
Scores
18 · 14 core
Phi-4
Microsoft · released 2024-12-12
text
Context
16K
Max out
16K
Input /1M
Output /1M
Cached /1M
Scores
11 · 7 core
Quality

Benchmark matrix

BenchmarkClaude Opus 4.7Phi-4ΔEdge
Reported by both · 3
GPQA Diamond94.2% 56.1% +38.1 ptClaude Opus 4.7
LMArena Elo1483.4 1216.6 +266.8Claude Opus 4.7
OTIS Mock AIME 2024-2025 (Epoch AI run)97.8% epoch13.8% epoch+84 ptClaude Opus 4.7
Only Claude Opus 4.7 reports · 14
SWE-bench Verified87.6% not reported
AIME 202695.8% matharenanot reported
Humanity's Last Exam (no tools)46.9% not reported
BrowseComp79.8% not reported
FrontierMath Tier 4 v2 (Epoch AI run)31.7% epochnot reported
FrontierMath Tiers 1-3 v2 (Epoch AI run)70.2% epochnot reported
Humanity's Last Exam (with tools)54.7% not reported
OSWorld-Verified82.8% not reported
SimpleQA Verified51.7% epochnot reported
SWE-bench Multilingual80.5% not reported
SWE-bench Multimodal34.5% not reported
SWE-Bench Pro64.3% not reported
SWE-bench Verified (Epoch AI run)83.5% epochnot reported
Terminal-Bench 2.166.1% not reported
Only Phi-4 reports · 7
MMLUnot reported84.8%
MMLU-Pronot reported70.4%
HumanEvalnot reported82.6%
ArenaHardnot reported75.4%
HumanEval+not reported82.8%
IFEvalnot reported63%
MATHnot reported80.4%
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 Claude Opus 4.7 minus Phi-4 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

SpecClaude Opus 4.7Phi-4Edge
Context window1M tokens16K tokensClaude Opus 4.7
Max output128K tokens16K tokensClaude Opus 4.7
Input price / 1M$5
Output price / 1M$25
Cached input / 1M$0.5
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$30
Modalitiestext · visiontextClaude Opus 4.7
Released2026-04-162024-12-12
Cited benchmark scores1811
Reliability

Provider status

All providers
More matchups

Claude Opus 4.7 vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude Opus 4.7 and Phi-4 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.