Claude Sonnet 4.5 vs Claude Sonnet 4.6
Why this pair: Consecutive Claude Sonnet releases
Benchmark Performance
Available Benchmarks
| Benchmark | Claude Sonnet 4.5 | Claude Sonnet 4.6 |
|---|---|---|
| ARC-AGI-1verified-v1-b2e2a31b3d53 · verified_score · leader | 63.6774% of row best · percent · Claude Sonnet 4.5 (Thinking 32K) | 86.50100% of row best · percent · Claude Sonnet 4.6 (High) |
| ARC-AGI-2verified-v2-326661568d5f · verified_score · leader | 13.6123% of row best · percent · Claude Sonnet 4.5 (Thinking 32K) | 60.42100% of row best · percent · Claude Sonnet 4.6 (High) |
| LMArena Document Arenadocument-2026-07-30-011508720696 · arena_rating · leader | 1,446.1998% of row best · rating · claude-sonnet-4-5-20250929; 95% CI [1439.60004073, 1452.78970477]; votes 28634; rank 22 | 1,482.80100% of row best · rating · claude-sonnet-4-6; 95% CI [1476.49799837, 1489.09368537]; votes 54427; rank 8 |
| LMArena Search Arenasearch-2026-08-24-011508720696 · arena_rating · leader | 1,158.4695% of row best · rating · claude-sonnet-4-5-search; 95% CI [1153.41447529, 1163.49714967]; votes 127378; rank 24 | 1,221.23100% of row best · rating · claude-sonnet-4-6-search; 95% CI [1216.39472071, 1226.06821163]; votes 134905; rank 7 |
| LMArena Text Arenatext-2026-09-01-011508720696 · arena_rating · leader | 1,433.9598% of row best · rating · claude-sonnet-4-5-20250929-high-32k; 95% CI [1431.13754052, 1436.75329939]; votes 81031; rank 79 | 1,458.01100% of row best · rating · claude-sonnet-4-6; 95% CI [1454.41608210, 1461.60383515]; votes 66343; rank 32 |
| ToneBench2026-08-28-10-task-cd9819ab6e4d · overall_score · leader | 77.2592% of row best · points · Claude Sonnet 4.5 · 2,441 output tokens / case | 83.63100% of row best · points · Claude Sonnet 4.6 · 2,525 output tokens / case |
| Overall ResultCounted from the protocol-matched rows above | 0 benchmark wins | 6 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.
Technical Differences
Side-by-Side Facts
| Field | Claude Sonnet 4.5 | Claude Sonnet 4.6 |
|---|---|---|
| Developer | Anthropic | Anthropic |
| Family | Claude 4 | Claude 4 |
| Model | Claude Sonnet 4.5 | Claude Sonnet 4.6 |
| Version | Claude Sonnet 4.5 | Claude Sonnet 4.6 |
| Lifecycle | active | active |
| Released | 2025-09-29 | 2026-02-17 |
| Knowledge cutoff | 2025-01-01 | 2025-08-01 |
| Input modalities | Text, Image | Text, Image |
| Output modalities | Text | Text |
| Context window | 200,000 | 1,000,000 |
| 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) | Anthropic (Standard), Deepinfra (Standard) |
| Capabilities | chat, generation, reasoning, structured_outputs, tools | chat, generation, reasoning, structured_outputs, tools |
15 comparable fields · 6 material differences · Editorially curated pair passes the primary-source comparison gate
Claude Sonnet 4.5 Capabilities
Claude Sonnet 4.6 Capabilities
Internal Comparison Graph
Related Comparisons
| A | Pair | B | Context |
|---|---|---|---|
Claude Opus 4.5Anthropic | vs | Claude Sonnet 4.5Anthropic | family variantsimage, text |
Claude Opus 4.6Anthropic | vs | Claude Sonnet 4.6Anthropic | family variantsimage, text |
Claude Opus 4.7Anthropic | vs | Claude Sonnet 4.6Anthropic | family variantsimage, text |
Claude Sonnet 4.6Anthropic | vs | Claude Sonnet 5Anthropic | family variantsimage, text |
Claude Sonnet 4.5Anthropic | vs | Claude Sonnet 5Anthropic | family variantsimage, text |
Claude Sonnet 4.5Anthropic | vs |  o3OpenAI | cross-developer peersimage, text |
Claude Sonnet 4.5Anthropic | vs | o3-proOpenAI | cross-developer peersimage, text |
Claude Sonnet 4.6Anthropic | vs |  Qwen3.7 FlashQwen | cross-developer peersimage, text |
Claude Sonnet 4.6Anthropic | vs | Grok 4.3xAI | cross-developer peersimage, text |
Claude Sonnet 4.6Anthropic | vs | GPT-5.4OpenAI | cross-developer peersimage, text |
Claude Sonnet 4.5Anthropic | vs | Qwen3 VL FlashQwen | cross-developer peersimage, text |
Claude Sonnet 4.5Anthropic | vs | GPT-5 NanoOpenAI | cross-developer peersimage, text |
Primary Evidence
Sources and Freshness
Questions
Claude Sonnet 4.5 vs Claude Sonnet 4.6 FAQs
Is Claude Sonnet 4.5 or Claude Sonnet 4.6 better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both Claude Sonnet 4.5 and Claude Sonnet 4.6, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, Claude Sonnet 4.5 or Claude Sonnet 4.6?+
Claude Sonnet 4.5 is $3.00 and Claude Sonnet 4.6 is $3.00 per million tokens, so they are tied on this metric. Claude Sonnet 4.5 is $15.00 and Claude Sonnet 4.6 is $15.00 per million tokens, so they are tied on this metric.
Which has a larger context window, Claude Sonnet 4.5 or Claude Sonnet 4.6?+
Claude Sonnet 4.6 has the larger sourced context window. Claude Sonnet 4.5 supports 200,000 and Claude Sonnet 4.6 supports 1,000,000.
Which performs better in benchmarks, Claude Sonnet 4.5 or Claude Sonnet 4.6?+
Claude Sonnet 4.6 leads the current overall benchmark count. The result uses 6 protocol-matched benchmarks from 3 publishers; it is not a universal quality score.
Can Claude Sonnet 4.5 or Claude Sonnet 4.6 be self-hosted?+
Both models have the same recorded self-hosting status: unsupported. Claude Sonnet 4.5 is not marked open weight; Claude Sonnet 4.6 is not marked open weight.
Can Claude Sonnet 4.5 and Claude Sonnet 4.6 understand images?+
Claude Sonnet 4.5 is documented with image input; Claude Sonnet 4.6 is documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, Claude Sonnet 4.5 or Claude Sonnet 4.6?+
Claude Sonnet 4.6 has the larger sourced maximum output: Claude Sonnet 4.5 supports 64,000 and Claude Sonnet 4.6 supports 128,000 output tokens.
Do Claude Sonnet 4.5 and Claude Sonnet 4.6 support reasoning and tool use?+
Claude Sonnet 4.5: reasoning, tool calling, and image input. Claude Sonnet 4.6: reasoning, tool calling, and image input. Feature support does not establish relative quality.
Which is available from more inference providers, Claude Sonnet 4.5 or Claude Sonnet 4.6?+
Claude Sonnet 4.5 has 1 sourced provider route; Claude Sonnet 4.6 has 2, so Claude Sonnet 4.6 has broader tracked availability.
Which offers better value, Claude Sonnet 4.5 or Claude Sonnet 4.6?+
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.