The Known Good Updated 25 Jul 2026
claude-haiku-4-5-20251001 vs DeepSeek: DeepSeek V3 ·Anthropic vs DeepSeek

claude-haiku-4-5-20251001 vs DeepSeek: DeepSeek V3 — head-to-head comparison

claude-haiku-4-5-20251001 profile DeepSeek: DeepSeek V3 profile All comparisons
claude-haiku-4-5-20251001 — Anthropic
Quality
#38 of 61
56based on 3 of 6 evaluations
Known Good Index
Speed
unranked
—
Output tokens per second
Price
unranked
—
Blended per 1M tokens
Cache hit price
unranked
—
per 1M tokens
Context
unranked
—
tokens
DeepSeek: DeepSeek V3 — DeepSeek
Quality
#44 of 61
44based on 3 of 6 evaluations
Known Good Index
Speed
#279 of 316
21.0
Output tokens per second
Price
#105 of 340
$0.35
Blended per 1M tokens
In $0.20 · Out $0.80
Cache hit price
#10 of 206
$0.003
per 1M tokens (−99%)
Context
#225 of 345
164k
tokens (~300 pages)
Summary

On the Known Good Index, claude-haiku-4-5-20251001 scores 56 and DeepSeek: DeepSeek V3 scores 44 — a 12-point lead for claude-haiku-4-5-20251001. They share 3 published evaluations, with claude-haiku-4-5-20251001 ahead on 3 and DeepSeek: DeepSeek V3 ahead on 0.

Published pricing is tracked for DeepSeek: DeepSeek V3 only, at $0.35 per 1M tokens blended.

claude-haiku-4-5-20251001 is proprietary; DeepSeek: DeepSeek V3 is open weights under Open weights (restricted use). 3 tracked hosts serve one or both.

Generated from tracked data on 26 Jul 2026 · how these comparisons are computed →

At a glance
Metricclaude-haiku-4-5-20251001DeepSeek: DeepSeek V3
Known Good Index 56 based on 3 of 6 evaluations 44 based on 3 of 6 evaluations
Blended $/1M — $0.35
Output tok/s — 21
Context window — 164k
Providers 0 3
Jump to section

Quality

Known Good Index and the capability indices, side by side

IndicesComponents
Index scores

Each index is min-max normalised across tracked models and scaled 0–100 from published evaluations. We do not run these evaluations.

Metricclaude-haiku-4-5-20251001DeepSeek: DeepSeek V3
Known Good Index 56 44
Mathematics Index 82 40
Science Index 71 53
Reasoning Index — 52
Agentic Index 30 —
Openness Index 5 60
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = claude-haiku-4-5-20251001 · marker = DeepSeek: DeepSeek V3 · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond71 / 57
MATH / AIME67 / 16
MATH Level 596 / 65

Right-hand figures read claude-haiku-4-5-20251001 / DeepSeek: DeepSeek V3. claude-haiku-4-5-20251001 leads on 3 of 3, DeepSeek: DeepSeek V3 on 0.

The Known Good

Arena Elo

Human preference rating from blind pairwise votes

Arena ratings

Elo from blind pairwise votes, ingested from Arena. Higher is better.

Metricclaude-haiku-4-5-20251001DeepSeek: DeepSeek V3
Text Arena 1,393 1,333
Text Arena (style controlled) 1,412 1,358
The Known Good

Price & Cost

Published API pricing by token type

Per token typeCache discount
Published pricing

USD per 1M tokens. Blended is a 3:1 input:output mix. Live from OpenRouter, cross-checked against models.dev. Lower is better.

Metricclaude-haiku-4-5-20251001DeepSeek: DeepSeek V3
Input $/1M — $0.20
Output $/1M — $0.80
Blended $/1M — $0.35
Cache read $/1M — $0.003
The Known Good
We publish blended price rather than cost-per-task. Cost-per-task requires token counts from an evaluation suite we do not run. Blended price is computed from published rates and is fully reproducible — see the pricing methodology.

Context Window

Maximum input accepted and maximum output emitted

Context and output limits

Provider-declared limits, from metadata via models.dev and OpenRouter. Higher is better.

Metricclaude-haiku-4-5-20251001DeepSeek: DeepSeek V3
Context window — 164k
Max output tokens — 16k
The Known Good

Speed & Latency

Median throughput and time to first token across hosting providers

Output speedTime to first token
Throughput and latency

Medians across all tracked providers, derived from OpenRouter endpoint telemetry.

Metricclaude-haiku-4-5-20251001DeepSeek: DeepSeek V3
Output tokens/s — 21
Time to first token — 1.1s
The Known Good

Providers

Which hosts serve each model, and at what price and speed

3 hosts
Full provider benchmarks →
Provider claude-haiku-4-5-20251001 blendedclaude-haiku-4-5-20251001 tok/s DeepSeek: DeepSeek V3 blendedDeepSeek: DeepSeek V3 tok/s
StreamLake — — $0.35 25
DeepInfra — — $0.46 23
Novita — — $0.62 18

Per-host pricing and telemetry from OpenRouter. A dash means that host does not serve that model.

The Known Good
Sources for this page
Pricing & providers — OpenRouter Metadata — models.dev Benchmarks — Epoch AI (CC-BY 4.0)Elo — Arena Full attribution →