Compare / Claude Opus 4.6 vs DeepSeek-V4-Flash (0731)

Claude Opus 4.6 vs DeepSeek-V4-Flash (0731)

Which is cheaper, which is more capable, and which does better at each kind of work, from 5 results on 2 sources that measured both models.

AnthropicClaude Opus 4.6 Released 5 Feb 2026 · $5.00 in · $25.00 out
DeepSeekDeepSeek-V4-Flash (0731) Released 31 Jul 2026 · $0.13 in · $0.40 out
Claude Opus 4.6 wins 2DeepSeek-V4-Flash (0731) wins 3

Of the 5 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee). See also Anthropic vs DeepSeek, every model from both labs.

Claude Opus 4.6 or DeepSeek-V4-Flash (0731)? The short answer

Pick DeepSeek-V4-Flash (0731): it scores higher (Intelligence Index 34.3 against 31.9) and costs less.

  • DeepSeek-V4-Flash (0731) is cheaper: $0.20 against $10.00 per million tokens, 51 times less.
  • DeepSeek-V4-Flash (0731) scores higher on the Artificial Analysis Intelligence Index: 34.3 against 31.9.
  • DeepSeek-V4-Flash (0731) is newer: released 31 Jul 2026, against 5 Feb 2026 for Claude Opus 4.6.
  • On third-party benchmarks, on the results both models have: Claude Opus 4.6 does better for sticking to the facts; DeepSeek-V4-Flash (0731) for reasoning and knowledge.

Head to head

31.9
Intelligence Index
34.3
$10.00
Price per million tokens, blendedlower is better
$0.20
1,000,000
Context window, tokens
1,048,576

Every fact side by side

Claude Opus 4.6DeepSeek-V4-Flash (0731)
Price per million tokens$5.00 in · $25.00 out$0.13 in · $0.40 out
Blended (3 in : 1 out)$10.00$0.20
Cheapest host, blended$10.00 (Amazon Bedrock)$0.088 (Relace, FP4)
Intelligence Index31.934.3
Spring Prompt overall––
Output speed, tokens a second––
Context window1,000,000 tokens1,048,576 tokens
Released5 Feb 202631 Jul 2026 (newer)
WeightsClosedOpen
Developer based inthe USChina

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 18 of 159 43 of 159
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 27 of 51 not measured
Reasoning and knowledgeHard questions across science, maths and general knowledge 52 of 187 47 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 4 of 169 not measured
Sticking to the factsSummarising without inventing things, and factual answers 57 of 139 105 of 139

From our research

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureClaude Opus 4.6DeepSeek-V4-Flash (0731)
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 51 · 44 of 249 measured 31.9max reasoning 34.3max reasoning
GPQA Diamond% of questions, higher is better 47 · 35 of 232 measured 89.6%max reasoning 90.8%max reasoning
Humanity's Last Exam% of questions, higher is better 46 · 52 of 250 measured 39.9%max reasoning 38.6%max reasoning
SimpleQA Verified (Epoch AI) reported by SimpleQA Verified (Epoch AI) · 1 result
Correct answers% of questions, higher is better 31 · 54 of 76 measured 47.0%max reasoning 33.6%max reasoning
Show all 5 results (1 more)
MeasureClaude Opus 4.6DeepSeek-V4-Flash (0731)
Artificial Analysis reported by Artificial Analysis · 1 result
Long-context reasoning (AA-LCR)% of questions, higher is better 65 · 47 of 241 measured 78.0%max reasoning 79.7%max reasoning

Quick answers

Is Claude Opus 4.6 better than DeepSeek-V4-Flash (0731)?

Pick DeepSeek-V4-Flash (0731): it scores higher (Intelligence Index 34.3 against 31.9) and costs less.

Which is cheaper, Claude Opus 4.6 or DeepSeek-V4-Flash (0731)?

DeepSeek-V4-Flash (0731) is cheaper: $0.20 against $10.00 per million tokens, 51 times less.

Which is better for agents and tool use, Claude Opus 4.6 or DeepSeek-V4-Flash (0731)?

Claude Opus 4.6 ranks 18 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 43 for DeepSeek-V4-Flash (0731).

Which is better for reasoning and knowledge, Claude Opus 4.6 or DeepSeek-V4-Flash (0731)?

DeepSeek-V4-Flash (0731) ranks 47 of 187 models on sale for hard questions across science, maths and general knowledge, against 52 for Claude Opus 4.6.

Which is better for sticking to the facts, Claude Opus 4.6 or DeepSeek-V4-Flash (0731)?

Claude Opus 4.6 ranks 57 of 139 models on sale for summarising without inventing things, and factual answers, against 105 for DeepSeek-V4-Flash (0731).

Which has the bigger context window, Claude Opus 4.6 or DeepSeek-V4-Flash (0731)?

DeepSeek-V4-Flash (0731): 1,048,576 tokens, against 1,000,000 for Claude Opus 4.6.

Run Claude Opus 4.6 and DeepSeek-V4-Flash (0731) on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.