Claude Haiku 4.5 vs Claude Sonnet 4.5
At a Glance
| Compare | Claude Haiku 4.5Anthropic | Claude Sonnet 4.5Anthropic |
|---|---|---|
| Intelligence, Cost, and Efficiency | ||
| IntelligenceHigher is better · MM Intelligence v4.4 | #41 of 579.3 score · 2/3 sources · provisional · missing LiveBench · full-core range 6.2–39.6 | UnrankedNot in the 57-model eligible cohort |
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $1.00Anthropic ↗ · Sep 3, 2026 | $3.00Anthropic ↗ · Sep 3, 2026 |
| Output priceFrom · USD / 1M tokens | $5.00Anthropic ↗ · Sep 3, 2026 | $15.00Anthropic ↗ · Sep 3, 2026 |
| Context windowMaximum documented tokens | 200K | 200K |
| Model facts checked | Aug 28, 2026View model evidence → | Sep 3, 2026View model evidence → |
Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →
Available Benchmarks
| Benchmark | Claude Haiku 4.5 | Claude Sonnet 4.5 |
|---|---|---|
| ARC-AGI-1verified-v1-613c385b0c93 · verified_score · leader | 47.6775% 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-be40992860f9 · verified_score · leader | 4.0330% 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-2026-09-13-a64ca3b12b6e · arena_rating · leader | 1,419.9798% of row best · rating · claude-haiku-4-5-20251001; 95% CI [1414.09579972, 1425.83505080]; votes 34677; rank 37 | 1,449.81100% of row best · rating · claude-sonnet-4-5-20250929; 95% CI [1443.68972646, 1455.92640287]; votes 31455; rank 28 |
| LMArena Text Arenatext-2026-10-15-a64ca3b12b6e · arena_rating · leader | 1,396.6497% of row best · rating · claude-haiku-4-5-20251001; 95% CI [1394.24930739, 1399.03971640]; votes 149199; rank 159 | 1,434.58100% of row best · rating · claude-sonnet-4-5-20250929-high-32k; 95% CI [1431.82164426, 1437.34230911]; votes 83940; rank 88 |
| Overall ResultCounted from the protocol-matched rows above | 0 benchmark wins | 4 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.
Side-by-Side Facts
| Field | Claude Haiku 4.5 | Claude Sonnet 4.5 |
|---|---|---|
| Developer | Anthropic | Anthropic |
| Family | Claude 4 5 | Claude 4 |
| Model | Claude Haiku 4.5 | Claude Sonnet 4.5 |
| Version | Claude Haiku 4.5 | Claude Sonnet 4.5 |
| Lifecycle | active | active |
| Released | 2025-10-15 | 2025-09-29 |
| Knowledge cutoff | Unknown | 2025-01-01 |
| Input modalities | Text, Image | Text, Image |
| Output modalities | Text | Text |
| Context window | 200K | 200K |
| Total parameters | Unknown | Unknown |
| Active parameters | Unknown | Unknown |
| License | Unknown | Unknown |
| Open weights | No | No |
| API available | Yes | Yes |
| Self-hostable | No | No |
| Provider access | Anthropic (Standard), Deepinfra (Standard) | Anthropic (Standard) |
| Capabilities | chat, generation, reasoning, tools | chat, generation, reasoning, structured_outputs, tools |
Claude Haiku 4.5 Capabilities
Claude Sonnet 4.5 Capabilities
Related Comparisons
All image comparisons →| A | Pair | B | Context |
|---|---|---|---|
Claude Haiku 4.5Anthropic | vs | Claude Opus 4.5Anthropic | family variantsimage, text |
Claude Haiku 4.5Anthropic | vs | Claude Opus 4.8Anthropic | family variantsimage, text |
Claude Haiku 4.5Anthropic | vs | Claude Opus 5Anthropic | family variantsimage, text |
Claude Haiku 4.5Anthropic | vs |  Gemini Computer UseGoogle DeepMind | cross-developer peerstext |
Claude Haiku 4.5Anthropic | vs |  Ministral-3-14B-Reasoning-2512Mistral AI | cross-developer peersimage, text |
Claude Haiku 4.5Anthropic | vs | Ministral-3-3B-Reasoning-2512Mistral AI | cross-developer peersimage, text |
Claude Haiku 4.5Anthropic | vs | Ministral-3-8B-Reasoning-2512Mistral AI | cross-developer peersimage, text |
Claude Haiku 4.5Anthropic | vs |  GPT-4oOpenAI | cross-developer peersimage, text |
Claude Haiku 4.5Anthropic | vs | GPT-4o MiniOpenAI | cross-developer peersimage, text |
Claude Haiku 4.5Anthropic | vs | o3OpenAI | cross-developer peersimage, text |
Claude Haiku 4.5Anthropic | vs | o3-proOpenAI | cross-developer peersimage, text |
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?+
Claude Haiku 4.5 is $1.00 and Claude Sonnet 4.5 is $3.00 per million tokens, so Claude Haiku 4.5 is cheaper on this metric. Claude Haiku 4.5 is $5.00 and Claude Sonnet 4.5 is $15.00 per million tokens, so Claude Haiku 4.5 is cheaper on this metric.
Which has a larger context window, Claude Haiku 4.5 or Claude Sonnet 4.5?+
Both models have the same sourced context window: 200,000 tokens each.
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 sourced 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 documented with image input; Claude Sonnet 4.5 is 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?+
Both models have the same sourced maximum output: 64,000 tokens each.
Do Claude Haiku 4.5 and Claude Sonnet 4.5 support reasoning and tool use?+
Claude Haiku 4.5: reasoning, tool calling, and image input. Claude Sonnet 4.5: reasoning, tool calling, and image input. 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.