Claude Sonnet 4.6 vs Claude Sonnet 5
At a Glance
| Compare | Claude Sonnet 4.6Anthropic | Claude Sonnet 5Anthropic |
|---|---|---|
| Intelligence, Cost, and Efficiency | ||
| IntelligenceHigher is better · MM Intelligence v4.4 | UnrankedNot in the 57-model eligible cohort | #18 of 5763.1 score · 2/3 sources · provisional · missing ARC-AGI-2 · full-core range 42.1–75.4 |
| CostLower is better · Published-token output estimate | UnrankedNot in the 27-model eligible cohort | #20 of 27$0.194 per LiveBench case |
| EfficiencyHigher is better · MM Efficiency v1.9 | UnrankedNot in the 27-model eligible cohort | #21 of 2743.5 score · 2/3 sources · provisional · missing ARC-AGI-2 · full-core range 33.0–49.6 |
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $3.00Anthropic ↗ · Sep 3, 2026 | $2.00Anthropic ↗ · Sep 3, 2026 |
| Output priceFrom · USD / 1M tokens | $15.00Anthropic ↗ · Sep 3, 2026 | $10.00Anthropic ↗ · Sep 3, 2026 |
| Context windowMaximum documented tokens | 1,000K | 1,000K |
| Model facts checked | Sep 3, 2026View model evidence → | Aug 28, 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 Sonnet 4.6 | Claude Sonnet 5 |
|---|---|---|
| LMArena Document Arenadocument-2026-09-13-a64ca3b12b6e · arena_rating · leader | 1,482.24100% of row best · rating · claude-sonnet-4-6; 95% CI [1476.36427265, 1488.10617859]; votes 57813; rank 11 | 1,466.1499% of row best · rating · claude-sonnet-5-high; 95% CI [1458.49407458, 1473.77896309]; votes 7411; rank 17 |
| LMArena Text Arenatext-2026-10-15-a64ca3b12b6e · arena_rating · leader | 1,457.87100% of row best · rating · claude-sonnet-4-6; 95% CI [1454.37156748, 1461.36302648]; votes 70931; rank 41 | 1,442.1299% of row best · rating · claude-sonnet-5-high; 95% CI [1438.01344792, 1446.22951308]; votes 49595; rank 72 |
| LMArena Vision Arenavision-2026-10-09-a64ca3b12b6e · arena_rating · statistical tie | 1,282.47100% of row best · rating · claude-sonnet-4-6; 95% CI [1276.33534417, 1288.60341882]; votes 27422; rank 34 | 1,273.9299% of row best · rating · claude-sonnet-5-high; 95% CI [1267.02186706, 1280.81063637]; votes 13503; rank 41 |
| LiveBench2026-06-25-90f8d44da965 · overall · leader | 77.1196% of row best · percent · claude-sonnet-4-6-thinking-auto-medium-effort · 13,226 output tokens / case | 80.01100% of row best · percent · claude-sonnet-5-xhigh-effort · 19,428 output tokens / case |
| ToneBench2026-10-17-10-task-e9c76358afb2 · overall_score · unverified | 75.9996% of row best · points · Claude Sonnet 4.6 (high) · 41,616 output tokens / case | 79.21100% of row best · points · Claude Sonnet 5 (max effort) · 66,953 output tokens / case |
| Overall ResultCounted from the protocol-matched rows above · 1 tie | 2 benchmark winsOverall lead | 1 benchmark win |
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 Sonnet 4.6 | Claude Sonnet 5 |
|---|---|---|
| Developer | Anthropic | Anthropic |
| Family | Claude 4 | Claude 5 |
| Model | Claude Sonnet 4.6 | Claude Sonnet 5 |
| Version | Claude Sonnet 4.6 | Claude Sonnet 5 |
| Lifecycle | active | active |
| Released | 2026-02-17 | 2026-06-30 |
| Knowledge cutoff | 2025-08-01 | Unknown |
| Input modalities | Text, Image | Text, Image |
| Output modalities | Text | Text |
| Context window | 1,000K | 1,000K |
| 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), Deepinfra (Standard), Openrouter (Standard) |
| Capabilities | chat, generation, reasoning, structured_outputs, tools | chat, generation, reasoning, tools |
Claude Sonnet 4.6 Capabilities
Claude Sonnet 5 Capabilities
Related Comparisons
All image comparisons →| A | Pair | B | Context |
|---|---|---|---|
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 4.5Anthropic | vs | Claude Sonnet 4.6Anthropic | family variantsimage, text |
Claude Sonnet 4.6Anthropic | vs | Seed 2.0 CodeByteDance Seed | cross-developer peerstext |
Claude Sonnet 4.6Anthropic | vs |  GPT-5 MiniOpenAI | cross-developer peersimage, text |
Claude Sonnet 4.6Anthropic | vs | GPT-5.4OpenAI | cross-developer peersimage, text |
Claude Sonnet 4.6Anthropic | vs | GPT-5.4 ProOpenAI | cross-developer peersimage, text |
Claude Sonnet 4.6Anthropic | vs | GPT-5.5OpenAI | cross-developer peersimage, text |
Claude Sonnet 4.6Anthropic | vs | GPT-5.5 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 |
Primary Evidence
Sources and Freshness
Questions
Claude Sonnet 4.6 vs Claude Sonnet 5 FAQs
Is Claude Sonnet 4.6 or Claude Sonnet 5 better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both Claude Sonnet 4.6 and Claude Sonnet 5, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, Claude Sonnet 4.6 or Claude Sonnet 5?+
Claude Sonnet 4.6 is $3.00 and Claude Sonnet 5 is $2.00 per million tokens, so Claude Sonnet 5 is cheaper on this metric. Claude Sonnet 4.6 is $15.00 and Claude Sonnet 5 is $10.00 per million tokens, so Claude Sonnet 5 is cheaper on this metric.
Which has a larger context window, Claude Sonnet 4.6 or Claude Sonnet 5?+
Both models have the same sourced context window: 1,000,000 tokens each.
Which performs better in benchmarks, Claude Sonnet 4.6 or Claude Sonnet 5?+
Claude Sonnet 4.6 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 Sonnet 4.6 or Claude Sonnet 5 be self-hosted?+
Both models have the same sourced self-hosting status: unsupported. Claude Sonnet 4.6 is not marked open weight; Claude Sonnet 5 is not marked open weight.
Can Claude Sonnet 4.6 and Claude Sonnet 5 understand images?+
Claude Sonnet 4.6 is documented with image input; Claude Sonnet 5 is documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, Claude Sonnet 4.6 or Claude Sonnet 5?+
Both models have the same sourced maximum output: 128,000 tokens each.
Do Claude Sonnet 4.6 and Claude Sonnet 5 support reasoning and tool use?+
Claude Sonnet 4.6: reasoning, tool calling, and image input. Claude Sonnet 5: reasoning, tool calling, and image input. Feature support does not establish relative quality.
Which is available from more inference providers, Claude Sonnet 4.6 or Claude Sonnet 5?+
Claude Sonnet 4.6 has 2 sourced provider routes; Claude Sonnet 5 has 3, so Claude Sonnet 5 has broader tracked availability.
Which offers better value, Claude Sonnet 4.6 or Claude Sonnet 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.