ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Haiku 4.5vsGPT-5 nano

Claude Haiku 4.5 leads 3 of 4 shared benchmarks. GPT-5 nano is 13.3x cheaper per token. GPT-5 nano has the larger context window (400K tokens).

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

Shared benchmarks
3 – 1
Claude Haiku 4.5 leads
Cheaper per token
GPT-5 nano
13.3x cheaper, input + output
Larger context
GPT-5 nano
400K tokens
Provider uptime (30d)
100% · 95.5923%
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 nano
OpenAI · released 2025-08-07
textvision
Context
400K
Max out
128K
Input /1M
$0.05
Output /1M
$0.4
Cached /1M
$0.005
Scores
7 · 7 core
Quality

Benchmark matrix

BenchmarkClaude Haiku 4.5GPT-5 nanoΔEdge
Reported by both · 4
SWE-bench Verified73.3% 54.7% +18.6 ptClaude Haiku 4.5
GPQA Diamond71.2% epoch69.4% epoch+1.8 ptClaude Haiku 4.5
OTIS Mock AIME 2024-2025 (Epoch AI run)66.7% epoch81.1% epoch-14.4 ptGPT-5 nano
SimpleQA Verified13.2% epoch11.7% epoch+1.5 ptClaude Haiku 4.5
Only Claude Haiku 4.5 reports · 0
Claude Haiku 4.5 reports nothing GPT-5 nano does not.
Only GPT-5 nano reports · 3
AIME 2025not reported85% matharena
FrontierMath Tier 4 v2 (Epoch AI run)not reported2.4% epoch
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported20% 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 nano 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 nanoEdge
Context window200K tokens400K tokensGPT-5 nano
Max output64K tokens128K tokensGPT-5 nano
Input price / 1M$1 $0.05 GPT-5 nano
Output price / 1M$5 $0.4 GPT-5 nano
Cached input / 1M$0.1 $0.005 GPT-5 nano
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$6$0.45GPT-5 nano
Modalitiestext · visiontext · visionTie
Released2025-10-152025-08-07
Cited benchmark scores47
Reliability

Provider status

All providers
More matchups

Claude Haiku 4.5 vs …

More matchups

GPT-5 nano vs …

Built by Respan
Which one wins on your data?

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