Claude Opus 4.6 vs o3
Claude Opus 4.6 leads o3 on the Artificial Analysis Intelligence Index, 31.9 to 20.2, and o3 costs 3.1x less per output token ($8.00 vs $25.00 per million). Updated October 22, 2026; 82 benchmarks have a result for both.
Claude Opus 4.6 or o3: which to pick
Only Claude Opus 4.6 has a coding score, 57.2 on the Vibe Coding Index; o3 has none, so the two cannot be ranked on coding.
Pick o3 for output tokens 3.1x cheaper ($8.00 vs $25.00 per million) and a lower cost per solved task ($0.571 against $1.56).
- Shared results
- 82
- Claude Opus 4.6 only
- 28
- o3 only
- 20
- Like-for-like categories
- 8 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only Claude Opus 4.6 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Claude Opus 4.6
Claude Opus 4.6 leads, 31.9 against 20.2.
Same board, both measured
Reasoning
GPQA Diamond
Claude Opus 4.6
Claude Opus 4.6 leads, 89.7% against 84.1%.
Same board, both measured
Math
AIME
Claude Opus 4.6
Claude Opus 4.6 leads, 95.6% against 85.3%.
Same board, both measured
Knowledge
MMLU Pro
Claude Opus 4.6
Claude Opus 4.6 leads, 89.1% against 85.6%.
Same board, both measured
Web design
Design Arena: websites
Claude Opus 4.6
Claude Opus 4.6 leads, 1291 against 1036.
Same board, both measured
Long documents
Listed context window
Claude Opus 4.6
Claude Opus 4.6 takes 1M tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
o3
Claude Opus 4.6 $0.018, o3 $0.0060 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
o3
Claude Opus 4.6 $1.56, o3 $0.571.
Published attempt cost and pass rate
At a glance
- Coding index
- Claude Opus 4.6 57.2 from 4 benchmarks, o3 not benchmarked.
- Widest category
- Web design, 27.7 points apart on average over 5 shared benchmarks.
- Widest single gap
- ARC-AGI-2: Claude Opus 4.6 69.2% against o3 6.5%, 62.6 points apart on a 0 to 100 scale.
- Output price
- Claude Opus 4.6 $25.00 against o3 $8.00 per million output tokens, 3.1x apart.
- Context window
- Claude Opus 4.6 takes 1M tokens, o3 200K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Claude Opus 4.6 | Bars | o3 | Ties |
|---|---|---|---|---|
| Coding | 7 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 3 | 0 | ||
| Reasoning | 14 | 2 | ||
| Math | 5 | 0 | ||
| Knowledge | 10 | 3 | ||
| Web design | 5 | 0 | ||
| General | 30 | 1 | ||
| All shared boards | 76 | 6 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index70
| Benchmark | Claude Opus 4.6 | o3 | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 81.3% | Only o3 measured |
| SWE-bench Verified | 75.6% | 58.4% | Claude Opus 4.6 |
| SWE-bench Multimodal | Not measured | 36.0% | Only o3 measured |
| SWE-bench Multilingual | 72.0% | Not measured | Only Claude Opus 4.6 measured |
| LMArena WebDev | 1547 | Not measured | Only Claude Opus 4.6 measured |
| LiveCodeBench (Vals AI) | 84.7% | 83.9% | Claude Opus 4.6 |
| SWE-bench Verified (Vals AI) | 78.2% | Not measured | Only Claude Opus 4.6 measured |
| Vibe Code Bench (Vals AI) | 57.6% | Not measured | Only Claude Opus 4.6 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 80.8% | Only o3 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 48.5% | 37.1% | Claude Opus 4.6 |
| Terminal-Bench | 79.8% | Not measured | Only Claude Opus 4.6 measured |
| FrontierCode | 26.6% | Not measured | Only Claude Opus 4.6 measured |
| GSO-Bench | 41.2% | 8.8% | Claude Opus 4.6 |
| WeirdML | 78.0% | 52.4% | Claude Opus 4.6 |
| Cybench | 93.0% | Not measured | Only Claude Opus 4.6 measured |
| ALE-Bench | Not measured | 933.5 | Only o3 measured |
| LMArena Text: coding | 1534 | 1407 | Claude Opus 4.6 |
| LMArena Text: software and IT | 1527 | 1415 | Claude Opus 4.6 |
| LMArena WebDev: React | 1539 | Not measured | Only Claude Opus 4.6 measured |
| LMArena WebDev: HTML | 1559 | Not measured | Only Claude Opus 4.6 measured |
| LMArena WebDev: from an image | 1543 | Not measured | Only Claude Opus 4.6 measured |
| SciCode | Not measured | 9.2% | Only o3 measured |
| Neither model has a result on the other 17 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Opus 4.6 | o3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 31.9 | 20.2 | Claude Opus 4.6 |
| Epoch Capabilities Index | 155.7 | 146.7 | Claude Opus 4.6 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Claude Opus 4.6 | o3 | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1206 | Not measured | Only Claude Opus 4.6 measured |
| Design Arena: agents building full-stack apps | 1220 | Not measured | Only Claude Opus 4.6 measured |
| Design Arena: agents building mobile apps | 1207 | Not measured | Only Claude Opus 4.6 measured |
| Design Arena: agents building Android apps | 1197 | Not measured | Only Claude Opus 4.6 measured |
| Design Arena: agents building games | 1212 | Not measured | Only Claude Opus 4.6 measured |
| τ²-Bench Telecom | 92.1% | 80.7% | Claude Opus 4.6 |
| APEX-Agents | 46.3% | Not measured | Only Claude Opus 4.6 measured |
| METR time horizons | 78.9% | 65.4% | Claude Opus 4.6 |
| Remote Labor Index | 4.2% | Not measured | Only Claude Opus 4.6 measured |
| GDPval | Not measured | 30.8% | Only o3 measured |
| DeepResearch Bench | 55.3% | 45.2% | Claude Opus 4.6 |
| OSWorld | Not measured | 23.0% | Only o3 measured |
| Vending-Bench 2 | $8,018 | Not measured | Only Claude Opus 4.6 measured |
| Berkeley Function Calling Leaderboard (BFCL) | Not measured | 63.0% | Only o3 measured |
| BrowseComp-Plus | Not measured | 65.9% | Only o3 measured |
| Neither model has a result on the other 26 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index142
| Benchmark | Claude Opus 4.6 | o3 | Leader |
|---|---|---|---|
| GPQA Diamond | 89.7% | 84.1% | Claude Opus 4.6 |
| MMMU Pro (Vals AI) | 83.9% | 80.4% | Claude Opus 4.6 |
| GPQA Diamond (Artificial Analysis run) | 89.6% | 82.7% | Claude Opus 4.6 |
| Humanity's Last Exam (Artificial Analysis run) | 39.9% | 20.1% | Claude Opus 4.6 |
| GPQA Diamond (Epoch AI run) | 90.5% | 81.8% | Claude Opus 4.6 |
| ARC-AGI | 94.0% | 60.8% | Claude Opus 4.6 |
| ARC-AGI-2 | 69.2% | 6.5% | Claude Opus 4.6 |
| SimpleBench | 67.6% | 53.1% | Claude Opus 4.6 |
| Chess puzzles | 21.0% | 37.0% | o3 |
| Mystery game puzzles | 25.0% | 29.0% | o3 |
| EBR-bench | 12.7% | Not measured | Only Claude Opus 4.6 measured |
| VPCT | Not measured | 52.0% | Only o3 measured |
| LMArena Text: hard prompts | 1525 | 1402 | Claude Opus 4.6 |
| LMArena Text: expert | 1544 | 1402 | Claude Opus 4.6 |
| LMArena Text: hard prompts in English | 1530 | 1411 | Claude Opus 4.6 |
| LMArena Vision: diagrams | 1340 | 1220 | Claude Opus 4.6 |
| LMArena Vision: homework | 1337 | 1234 | Claude Opus 4.6 |
| Kagi LLM Benchmark | 83.6% | 67.6% | Claude Opus 4.6 |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Claude Opus 4.6 | o3 | Leader |
|---|---|---|---|
| AIME | 95.6% | 85.3% | Claude Opus 4.6 |
| MATH 500 (Vals AI) | Not measured | 94.6% | Only o3 measured |
| MGSM (Vals AI) | Not measured | 91.8% | Only o3 measured |
| AA Math Index | Not measured | 88.3 | Only o3 measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 88.3% | Only o3 measured |
| OTIS Mock AIME | 94.4% | 84.4% | Claude Opus 4.6 |
| FrontierMath, tiers 1 to 3 | 66.0% | 33.3% | Claude Opus 4.6 |
| FrontierMath, tier 4 | 26.8% | Not measured | Only Claude Opus 4.6 measured |
| ProofBench | 50.0% | Not measured | Only Claude Opus 4.6 measured |
| MATH level 5 | Not measured | 97.8% | Only o3 measured |
| LMArena Text: math | 1518 | 1426 | Claude Opus 4.6 |
| LMArena Text: mathematical work | 1525 | 1423 | Claude Opus 4.6 |
| Neither model has a result on the other 1 board here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index103
| Benchmark | Claude Opus 4.6 | o3 | Leader |
|---|---|---|---|
| MMLU Pro | 89.1% | 85.6% | Claude Opus 4.6 |
| LegalBench (Vals AI) | 85.3% | 83.8% | Claude Opus 4.6 |
| CaseLaw (Vals AI) | 62.1% | Not measured | Only Claude Opus 4.6 measured |
| CorpFin (Vals AI) | 67.0% | 59.7% | Claude Opus 4.6 |
| TaxEval (Vals AI) | 76.0% | 74.6% | Claude Opus 4.6 |
| MortgageTax (Vals AI) | 68.5% | 65.7% | Claude Opus 4.6 |
| MedQA (Vals AI) | 95.4% | 96.1% | o3 |
| MedCode (Vals AI) | 49.1% | 47.3% | Claude Opus 4.6 |
| MMLU Pro (Artificial Analysis run) | Not measured | 85.3% | Only o3 measured |
| SimpleQA Verified | 47.0% | 49.4% | o3 |
| GeoBench | Not measured | 74.0% | Only o3 measured |
| LMArena Text: science | 1519 | 1429 | Claude Opus 4.6 |
| LMArena Text: medicine and healthcare | 1504 | 1448 | Claude Opus 4.6 |
| LMArena Text: legal and government | 1512 | 1428 | Claude Opus 4.6 |
| LMArena Text: business and finance | 1497 | 1393 | Claude Opus 4.6 |
| FACTS Benchmark Suite | 41.5% | 44.4% | o3 |
| Neither model has a result on the other 2 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Claude Opus 4.6 | o3 | Leader |
|---|---|---|---|
| Design Arena: websites | 1291 | 1036 | Claude Opus 4.6 |
| Design Arena: UI components | 1281 | 1017 | Claude Opus 4.6 |
| Design Arena: game dev | 1277 | 1034 | Claude Opus 4.6 |
| Design Arena: data viz | 1279 | 1200 | Claude Opus 4.6 |
| Design Arena: 3D | 1273 | Not measured | Only Claude Opus 4.6 measured |
| Design Arena: all code categories | 1288 | 1020 | Claude Opus 4.6 |
| Design Arena: SVG | 1227 | Not measured | Only Claude Opus 4.6 measured |
| Design Arena: ASCII art | 1255 | Not measured | Only Claude Opus 4.6 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index301
| Benchmark | Claude Opus 4.6 | o3 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 51.6% | 41.8% | Claude Opus 4.6 |
| MedScribe (Vals AI) | 86.7% | 76.7% | Claude Opus 4.6 |
| IFBench | 53.1% | 71.4% | o3 |
| Long context reasoning (AA-LCR) | 78.0% | 74.7% | Claude Opus 4.6 |
| DTBench | 91.2% | 84.8% | Claude Opus 4.6 |
| LMCA | 55.8% | 39.7% | Claude Opus 4.6 |
| Fiction.LiveBench | Not measured | 88.9% | Only o3 measured |
| Creative writing (Lech Mazur) | Not measured | 83.9% | Only o3 measured |
| CL-bench | 20.7% | 17.8% | Claude Opus 4.6 |
| Furniture assembly | 28.3% | Not measured | Only Claude Opus 4.6 measured |
| CL-bench Life | 17.0% | Not measured | Only Claude Opus 4.6 measured |
| LMArena Text | 1501 | 1410 | Claude Opus 4.6 |
| LMArena Text: instruction following | 1521 | 1368 | Claude Opus 4.6 |
| LMArena Text: creative writing | 1505 | 1359 | Claude Opus 4.6 |
| LMArena Vision | 1316 | 1214 | Claude Opus 4.6 |
| LMArena Text: English | 1511 | 1417 | Claude Opus 4.6 |
| LMArena Text: non-English | 1488 | 1401 | Claude Opus 4.6 |
| LMArena Text: Chinese | 1551 | 1437 | Claude Opus 4.6 |
| LMArena Text: German | 1500 | 1420 | Claude Opus 4.6 |
| LMArena Text: Japanese | 1488 | 1403 | Claude Opus 4.6 |
| LMArena Text: Korean | 1464 | 1370 | Claude Opus 4.6 |
| LMArena Text: French | 1512 | 1430 | Claude Opus 4.6 |
| LMArena Text: Spanish | 1510 | 1395 | Claude Opus 4.6 |
| LMArena Text: Russian | 1497 | 1406 | Claude Opus 4.6 |
| LMArena Text: Polish | 1499 | 1438 | Claude Opus 4.6 |
| LMArena Text: multi-turn | 1511 | 1405 | Claude Opus 4.6 |
| LMArena Text: longer queries | 1518 | 1372 | Claude Opus 4.6 |
| LMArena Text: writing and language | 1502 | 1372 | Claude Opus 4.6 |
| LMArena Text: entertainment and media | 1492 | 1373 | Claude Opus 4.6 |
| LMArena Vision: English | 1324 | 1221 | Claude Opus 4.6 |
| LMArena Vision: Chinese | 1370 | 1237 | Claude Opus 4.6 |
| LMArena Vision: reading text | 1326 | 1218 | Claude Opus 4.6 |
| LMArena Vision: humor | 1314 | 1222 | Claude Opus 4.6 |
| LMArena Vision: captioning | Not measured | 1210 | Only o3 measured |
| LMArena Vision: recognizing things | 1274 | 1234 | Claude Opus 4.6 |
| LMArena Vision: creative writing | 1331 | 1201 | Claude Opus 4.6 |
| LMArena Document | 1507 | Not measured | Only Claude Opus 4.6 measured |
| Neither model has a result on the other 9 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Opus 4.6 | o3 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
o3 costs less
Repository review
50K input + 3K output tokens
o3 costs less
Agent loop
200K input + 10K output tokens
o3 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Anthropic Claude Opus 4.6 | OpenAI o3 |
|---|---|---|
| Maker | Anthropic | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | February 4, 2026 | April 16, 2025 |
| Context window | 1M | 200K |
| Input $/Mtok | $5.00 | $2.00 |
| Output $/Mtok | $25.00 | $8.00 |
| Coding index | 57.2 | Not benchmarked |
| Independent measurements behind it | 4 | 0 |
| Cost per solved task | $1.56 | $0.571 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Opus 4.6 better than o3 for coding?
Only Claude Opus 4.6 has a coding score, 57.2 on the Vibe Coding Index; o3 has none, so the two cannot be ranked on coding. Pick o3 for output tokens 3.1x cheaper ($8.00 vs $25.00 per million) and a lower cost per solved task ($0.571 against $1.56).
Which is cheaper, Claude Opus 4.6 or o3?
Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens; o3 costs $2.00 and $8.00. Per solved SWE-bench Verified task, Claude Opus 4.6 costs $1.56 and o3 $0.571.
Which has the bigger context window, Claude Opus 4.6 or o3?
Claude Opus 4.6, with 1M tokens against 200K.
How many benchmarks is the Claude Opus 4.6 vs o3 comparison based on?
82 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.6's coding index rests on 4 independent benchmarks and o3's on 0. Where only one model has a result, the page says so instead of naming a winner.