ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Haiku 4.5vsGPT-6 Astra

GPT-6 Astra leads 3 of 3 shared benchmarks. Claude Haiku 4.5 is 10x cheaper per token. GPT-6 Astra has the larger context window (1.1M tokens).

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

Shared benchmarks
0 – 3
GPT-6 Astra leads
Cheaper per token
Claude Haiku 4.5
10x cheaper, input + output
Larger context
GPT-6 Astra
1.1M tokens
Provider uptime (30d)
100% · 95.389%
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-6 Astra
OpenAI · released 2026-09-03
textvision
Context
1.1M
Max out
128K
Input /1M
$10
Output /1M
$50
Cached /1M
$1
Scores
8 · 5 core
Quality

Benchmark matrix

BenchmarkClaude Haiku 4.5GPT-6 AstraΔEdge
Reported by both · 3
GPQA Diamond71.2% epoch96% -24.8 ptGPT-6 Astra
OTIS Mock AIME 2024-2025 (Epoch AI run)66.7% epoch100% epoch-33.3 ptGPT-6 Astra
SimpleQA Verified13.2% epoch75.6% epoch-62.4 ptGPT-6 Astra
Only Claude Haiku 4.5 reports · 1
SWE-bench Verified73.3% not reported
Only GPT-6 Astra reports · 4
AutomationBenchnot reported41.4%
FrontierMath Tier 4 v2 (Epoch AI run)not reported97.6% epoch
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported93.7% epoch
Terminal-Bench Science 0.1not reported64.6%
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-6 Astra 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-6 AstraEdge
Context window200K tokens1.1M tokensGPT-6 Astra
Max output64K tokens128K tokensGPT-6 Astra
Input price / 1M$1 $10 Claude Haiku 4.5
Output price / 1M$5 $50 Claude Haiku 4.5
Cached input / 1M$0.1 $1 Claude Haiku 4.5
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$6$60Claude Haiku 4.5
Modalitiestext · visiontext · visionTie
Released2025-10-152026-09-03
Cited benchmark scores48
Reliability

Provider status

All providers
More matchups

Claude Haiku 4.5 vs …

More matchups

GPT-6 Astra vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude Haiku 4.5 and GPT-6 Astra on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.