ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Haiku 4.5vsGrok 4.6

Grok 4.6 leads 3 of 3 shared benchmarks. Claude Haiku 4.5 is 1.3x cheaper per token. Grok 4.6 has the larger context window (500K tokens).

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

Shared benchmarks
0 – 3
Grok 4.6 leads
Cheaper per token
Claude Haiku 4.5
1.3x cheaper, input + output
Larger context
Grok 4.6
500K tokens
Provider uptime (30d)
100% · —
Anthropic · xAI
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
Grok 4.6
xAI · released 2026-08-12
textvision
Context
500K
Max out
Input /1M
$2
Output /1M
$6
Cached /1M
$0.5
Scores
15 · 5 core
Quality

Benchmark matrix

BenchmarkClaude Haiku 4.5Grok 4.6ΔEdge
Reported by both · 3
GPQA Diamond71.2% epoch94% epoch-22.8 ptGrok 4.6
OTIS Mock AIME 2024-2025 (Epoch AI run)66.7% epoch99.2% epoch-32.5 ptGrok 4.6
SimpleQA Verified13.2% epoch49.3% epoch-36.1 ptGrok 4.6
Only Claude Haiku 4.5 reports · 1
SWE-bench Verified73.3% not reported
Only Grok 4.6 reports · 12
AA-Briefcasenot reported1577
APEX-Agentsnot reported57.5%
APEX-SWEnot reported56.4%
Artificial Analysis Intelligence Indexnot reported61
CursorBench 3.2not reported69.9%
DeepSWE v1.1not reported65.9%
FrontierCode v1.1 (Extended)not reported61.3%
FrontierMath Tier 4 v2 (Epoch AI run)not reported31.7% epoch
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported66% epoch
GDPVal-AA v2not reported1753
Harvey LAB (Vals)not reported15.8%
Terminal-Bench 3.0not reported26%
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 Grok 4.6 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 4.5Grok 4.6Edge
Context window200K tokens500K tokensGrok 4.6
Max output64K tokens
Input price / 1M$1 $2 Claude Haiku 4.5
Output price / 1M$5 $6 Claude Haiku 4.5
Cached input / 1M$0.1 $0.5 Claude Haiku 4.5
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$6$8Claude Haiku 4.5
Modalitiestext · visiontext · visionTie
Released2025-10-152026-08-12
Cited benchmark scores415
Reliability

Provider status

All providers
More matchups

Claude Haiku 4.5 vs …

More matchups

Grok 4.6 vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude Haiku 4.5 and Grok 4.6 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.