Claude Haiku 4.5 vs Claude Sonnet 4.5

Benchmark Performance

Available Benchmarks

BenchmarkClaude Haiku 4.5Claude Sonnet 4.5
ARC-AGI-1verified-v1-15fb467fd4fc · verified_score · leader47.6775% of row best · percent · Claude Haiku 4.5 (Thinking 32K)63.67100% of row best · percent · Claude Sonnet 4.5 (Thinking 32K)
ARC-AGI-2verified-v2-9a3db289984e · verified_score · leader4.0330% of row best · percent · Claude Haiku 4.5 (Thinking 32K)13.61100% of row best · percent · Claude Sonnet 4.5 (Thinking 32K)
LMArena Document Arenadocument-2026-07-30-011508720696 · arena_rating · leader1,423.0398% of row best · rating · claude-haiku-4-5-20251001; 95% CI [1416.59570790, 1429.45877492]; votes 30937; rank 301,446.19100% of row best · rating · claude-sonnet-4-5-20250929; 95% CI [1439.60004073, 1452.78970477]; votes 28634; rank 22
LMArena Text Arenatext-2026-09-01-011508720696 · arena_rating · leader1,395.2597% of row best · rating · claude-haiku-4-5-20251001; 95% CI [1392.70335168, 1397.78975878]; votes 124979; rank 1441,433.95100% of row best · rating · claude-sonnet-4-5-20250929-high-32k; 95% CI [1431.13754052, 1436.75329939]; votes 81031; rank 79
Overall ResultCounted from the protocol-matched rows above0 benchmark wins4 benchmark winsOverall lead

Third-party benchmark Only like-for-like primary-publisher results are shown; raw scores, relative scores, configuration, and token spend remain visible.

FieldAt a Glance
Anthropic · activeClaude Haiku 4.5Verified Aug 28, 2026
Anthropic · activeClaude Sonnet 4.5Verified Sep 3, 2026
Not a Valid ComparisonThese records do not share a sourced modality and workload.

Technical Differences

Side-by-Side Facts

Interactive only
FieldClaude Haiku 4.5Claude Sonnet 4.5
DeveloperAnthropicAnthropic
FamilyClaude 4 5Claude 4
ModelClaude Haiku 4.5Claude Sonnet 4.5
VersionClaude Haiku 4.5Claude Sonnet 4.5
Lifecycleactiveactive
Released2025-10-152025-09-29
Knowledge cutoffUnknown2025-01-01
Input modalitiesUnknownUnknown
Output modalitiesUnknownUnknown
Context window200,000200,000
Total parametersUnknownUnknown
Active parametersUnknownUnknown
LicenseUnknownUnknown
Open weightsNoNo
API availableYesYes
Self-hostableNoNo
Provider accessAnthropic (Standard), Deepinfra (Standard)Anthropic (Standard)
Capabilitieschat, generation, reasoning, toolschat, generation, reasoning, structured_outputs, tools

12 comparable fields · 6 material differences · Interactive comparison only; indexing gate not met

Claude Haiku 4.5 Capabilities

chatgenerationreasoningtools
Input price$1.00
Output price$5.00
Serving providers2
Canonical IDanthropic/claude-haiku-4-5

Claude Sonnet 4.5 Capabilities

chatgenerationreasoningstructured outputstools
Input price
Output price
Serving providers1
Canonical IDanthropic/claude-sonnet-4-5

Primary Evidence

Sources and Freshness

Questions

Claude Haiku 4.5 vs Claude Sonnet 4.5 FAQs

Is Claude Haiku 4.5 or Claude Sonnet 4.5 better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both Claude Haiku 4.5 and Claude Sonnet 4.5, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, Claude Haiku 4.5 or Claude Sonnet 4.5?+

Only Claude Haiku 4.5 has a directly sourced input price: $1.00 per million tokens. Only Claude Haiku 4.5 has a directly sourced output price: $5.00 per million tokens.

Which has a larger context window, Claude Haiku 4.5 or Claude Sonnet 4.5?+

Neither model has a larger sourced context window in this comparison. Claude Haiku 4.5 is 200,000 and Claude Sonnet 4.5 is 200,000.

Which performs better in benchmarks, Claude Haiku 4.5 or Claude Sonnet 4.5?+

Claude Sonnet 4.5 leads the current overall benchmark count. The result uses 4 protocol-matched benchmarks from 2 publishers; it is not a universal quality score.

Can Claude Haiku 4.5 or Claude Sonnet 4.5 be self-hosted?+

Both models have the same recorded self-hosting status: unsupported. Claude Haiku 4.5 is not marked open weight; Claude Sonnet 4.5 is not marked open weight.

Can Claude Haiku 4.5 and Claude Sonnet 4.5 understand images?+

Claude Haiku 4.5 is not documented with image input; Claude Sonnet 4.5 is not documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, Claude Haiku 4.5 or Claude Sonnet 4.5?+

Neither has a larger sourced maximum output. Claude Haiku 4.5 is 64,000 and Claude Sonnet 4.5 is 64,000.

Do Claude Haiku 4.5 and Claude Sonnet 4.5 support reasoning and tool use?+

Claude Haiku 4.5: reasoning and tool calling. Claude Sonnet 4.5: reasoning and tool calling. Feature support does not establish relative quality.

Which is available from more inference providers, Claude Haiku 4.5 or Claude Sonnet 4.5?+

Claude Haiku 4.5 has 2 sourced provider routes; Claude Sonnet 4.5 has 1, so Claude Haiku 4.5 has broader tracked availability.

Which offers better value, Claude Haiku 4.5 or Claude Sonnet 4.5?+

There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.

Send Feedback