ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Haiku 4.5vsGPT-5.4 mini

GPT-5.4 mini leads 3 of 3 shared benchmarks. GPT-5.4 mini is 1.1x cheaper per token. GPT-5.4 mini has the larger context window (400K tokens).

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

Shared benchmarks
0 – 3
GPT-5.4 mini leads
Cheaper per token
GPT-5.4 mini
1.1x cheaper, input + output
Larger context
GPT-5.4 mini
400K tokens
Provider uptime (30d)
100% · 95.3353%
Anthropic · OpenAI
Claude Haiku 4.5
Anthropic · released 2025-10-15
textvision
Context
200K
Max out
64K
Input /1M
$1
Output /1M
$5
Cached /1M
$0.1
Scores
4 · 4 core
GPT-5.4 mini
OpenAI · released 2026-03-17
textvision
Context
400K
Max out
128K
Input /1M
$0.75
Output /1M
$4.5
Cached /1M
$0.075
Scores
10 · 6 core
Quality

Benchmark matrix

BenchmarkClaude Haiku 4.5GPT-5.4 miniΔEdge
Reported by both · 3
GPQA Diamond71.2% epoch88% -16.8 ptGPT-5.4 mini
OTIS Mock AIME 2024-2025 (Epoch AI run)66.7% epoch88.9% epoch-22.2 ptGPT-5.4 mini
SimpleQA Verified13.2% epoch29.4% epoch-16.2 ptGPT-5.4 mini
Only Claude Haiku 4.5 reports · 1
SWE-bench Verified73.3% not reported
Only GPT-5.4 mini reports · 6
FrontierMath Tier 4 v2 (Epoch AI run)not reported9.8% epoch
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported51.2% epoch
OSWorld-Verifiednot reported72.1%
SWE-Bench Pronot reported54.4%
Terminal-Bench 2.0not reported60%
Toolathlonnot reported42.9%
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 Claude Haiku 4.5 minus GPT-5.4 mini 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 Haiku 4.5GPT-5.4 miniEdge
Context window200K tokens400K tokensGPT-5.4 mini
Max output64K tokens128K tokensGPT-5.4 mini
Input price / 1M$1 $0.75 GPT-5.4 mini
Output price / 1M$5 $4.5 GPT-5.4 mini
Cached input / 1M$0.1 $0.075 GPT-5.4 mini
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$6$5.25GPT-5.4 mini
Modalitiestext · visiontext · visionTie
Released2025-10-152026-03-17
Cited benchmark scores410
Reliability

Provider status

All providers
More matchups

Claude Haiku 4.5 vs …

More matchups

GPT-5.4 mini vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude Haiku 4.5 and GPT-5.4 mini on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.