ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Haiku 4.5vsGPT-5

GPT-5 leads 4 of 4 shared benchmarks. Claude Haiku 4.5 is 1.9x cheaper per token. GPT-5 has the larger context window (400K tokens).

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

Shared benchmarks
0 – 4
GPT-5 leads
Cheaper per token
Claude Haiku 4.5
1.9x cheaper, input + output
Larger context
GPT-5
400K tokens
Provider uptime (30d)
100% · 95.5679%
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
OpenAI · released 2025-08-07
textvision
Context
400K
Max out
128K
Input /1M
$1.25
Output /1M
$10
Cached /1M
$0.125
Scores
9 · 8 core
Quality

Benchmark matrix

BenchmarkClaude Haiku 4.5GPT-5ΔEdge
Reported by both · 4
SWE-bench Verified73.3% 74.9% -1.6 ptGPT-5
GPQA Diamond71.2% epoch86.2% epoch-15 ptGPT-5
OTIS Mock AIME 2024-2025 (Epoch AI run)66.7% epoch91.4% epoch-24.7 ptGPT-5
SimpleQA Verified13.2% epoch50.1% epoch-36.9 ptGPT-5
Only Claude Haiku 4.5 reports · 0
Claude Haiku 4.5 reports nothing GPT-5 does not.
Only GPT-5 reports · 4
AIME 2025not reported94.6%
FrontierMath Tier 4 v2 (Epoch AI run)not reported22% epoch
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported55.4% epoch
SWE-bench Verified (Epoch AI run)not reported73.6% epoch
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 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-5Edge
Context window200K tokens400K tokensGPT-5
Max output64K tokens128K tokensGPT-5
Input price / 1M$1 $1.25 Claude Haiku 4.5
Output price / 1M$5 $10 Claude Haiku 4.5
Cached input / 1M$0.1 $0.125 Claude Haiku 4.5
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$6$11.25Claude Haiku 4.5
Modalitiestext · visiontext · visionTie
Released2025-10-152025-08-07
Cited benchmark scores49
Reliability

Provider status

All providers
More matchups

Claude Haiku 4.5 vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude Haiku 4.5 and GPT-5 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.