ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude 3.5 SonnetvsPhi-4

Phi-4 leads 2 of 2 shared benchmarks. Claude 3.5 Sonnet has the larger context window (200K tokens).

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

Shared benchmarks
0 – 2
Phi-4 leads
Cheaper per token
list price, input + output
Larger context
Claude 3.5 Sonnet
200K tokens
Provider uptime (30d)
100% · —
Anthropic · Microsoft
Claude 3.5 Sonnet
Anthropic · released 2024-10-22
textvision
Context
200K
Max out
8K
Input /1M
$3
Output /1M
$15
Cached /1M
$0.3
Scores
4 · 4 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 3.5 SonnetPhi-4ΔEdge
Reported by both · 2
GPQA Diamond55.3% epoch56.1% -0.8 ptPhi-4
OTIS Mock AIME 2024-2025 (Epoch AI run)8.5% epoch13.8% epoch-5.3 ptPhi-4
Only Claude 3.5 Sonnet reports · 2
SWE-bench Verified49% not reported
AIME 20253.3% matharenanot reported
Only Phi-4 reports · 8
MMLUnot reported84.8%
MMLU-Pronot reported70.4%
HumanEvalnot reported82.6%
LMArena Elonot reported1216.6
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 3.5 Sonnet 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 3.5 SonnetPhi-4Edge
Context window200K tokens16K tokensClaude 3.5 Sonnet
Max output8K tokens16K tokensPhi-4
Input price / 1M$3
Output price / 1M$15
Cached input / 1M$0.3
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$18
Modalitiestext · visiontextClaude 3.5 Sonnet
Released2024-10-222024-12-12
Cited benchmark scores411
Reliability

Provider status

All providers
More matchups

Claude 3.5 Sonnet vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude 3.5 Sonnet and Phi-4 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.