Claude Opus 5.5 vs Phi 4
Updated October 21, 2026. 31 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
vs boards won of 31 shared
Decision reading
Only Claude Opus 5.5 has a coding score, 88.8 on the Vibe Coding Index; Phi 4 has none, so the two cannot be ranked on coding.
Phi 4 has the edge where output tokens cost 142.9x less.
Model AClaude Opus 5.5Anthropic88.8/1005 independent benchmarksNo cost per solved taskModel BPhi 4MicrosoftNot benchmarkedNo coding benchmarkNo cost per solved task
- Shared results
- 31
- Claude Opus 5.5 only
- 76
- Phi 4 only
- 14
- Like-for-like categories
- 6 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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 5.5 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Claude Opus 5.5
Claude Opus 5.5 leads, 57.6 against 5.9.
Same board, both measured
Web design
Design Arena: websites
No call
Only Claude Opus 5.5 has a Design Arena: websites result, 1336.
Directional only
General
Vals Index
No call
Only Claude Opus 5.5 has a Vals Index result, 70.2%.
Directional only
Long documents
Listed context window
Claude Opus 5.5
Claude Opus 5.5 takes 1M tokens against 16K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Phi 4
Claude Opus 5.5 $0.014, Phi 4 $0.0001 per turn.
List prices
At a glance
- Coding index
- Claude Opus 5.5 88.8 from 5 benchmarks, Phi 4 not benchmarked.
- Widest category
- Math, 58.4 points apart on average over 3 shared benchmarks.
- Widest single gap
- OTIS Mock AIME: Claude Opus 5.5 100.0% against Phi 4 13.8%, 86.3 points apart on a 0 to 100 scale.
- Output price
- Claude Opus 5.5 $20.00 against Phi 4 $0.14 per million output tokens, 142.9x apart.
- Context window
- Claude Opus 5.5 takes 1M tokens, Phi 4 16K.
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 5.5 | Bars | Phi 4 | Ties |
|---|---|---|---|---|
| Coding | 2 | 0 | ||
| Intelligence | 2 | 0 | ||
| Reasoning | 5 | 0 | ||
| Math | 3 | 0 | ||
| Knowledge | 4 | 0 | ||
| General | 15 | 0 | ||
| All shared boards | 31 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
| Benchmark | Claude Opus 5.5 | Phi 4 | Leader |
|---|---|---|---|
| LiveBench coding | 96.3% | Not measured | Only Claude Opus 5.5 measured |
| LMArena WebDev | 1807 | Not measured | Only Claude Opus 5.5 measured |
| Terminal-Bench 4 (Vals AI) | 65.2% | Not measured | Only Claude Opus 5.5 measured |
| Vibe Code Bench (Vals AI) | 90.3% | Not measured | Only Claude Opus 5.5 measured |
| Code migration (Vals AI) | 66.7% | Not measured | Only Claude Opus 5.5 measured |
| ProgramBench (Vals AI) | 18.5% | Not measured | Only Claude Opus 5.5 measured |
| IOI (Vals AI) | 95.1% | Not measured | Only Claude Opus 5.5 measured |
| Terminal-Bench 2.1 (Vals AI) | 87.6% | Not measured | Only Claude Opus 5.5 measured |
| SWE-bench Multimodal (Vals AI) | 70.2% | Not measured | Only Claude Opus 5.5 measured |
| Vibe Code Bench 1-100 (Vals AI) | 30.4% | Not measured | Only Claude Opus 5.5 measured |
| CyberBench (Vals AI) | 74.6% | Not measured | Only Claude Opus 5.5 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 23.1% | Only Phi 4 measured |
| SciCode | 66.9% | Not measured | Only Claude Opus 5.5 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 3.8% | Only Phi 4 measured |
| FrontierCode | 54.6% | Not measured | Only Claude Opus 5.5 measured |
| FrontierSWE | 62.3% | Not measured | Only Claude Opus 5.5 measured |
| MirrorCode | 77.4% | Not measured | Only Claude Opus 5.5 measured |
| ALE-Bench | 2147.4 | Not measured | Only Claude Opus 5.5 measured |
| LMArena Text: coding | 1545 | 1231 | Claude Opus 5.5 |
| LMArena Text: software and IT | 1538 | 1228 | Claude Opus 5.5 |
| LMArena WebDev: React | 1855 | Not measured | Only Claude Opus 5.5 measured |
| LMArena WebDev: HTML | 1753 | Not measured | Only Claude Opus 5.5 measured |
| LMArena WebDev: from an image | 1753 | Not measured | Only Claude Opus 5.5 measured |
| Neither model has a result on the other 15 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Opus 5.5 | Phi 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 57.6 | 5.9 | Claude Opus 5.5 |
| Epoch Capabilities Index | 168.8 | 130.5 | Claude Opus 5.5 |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index25 boards, none shared
| Benchmark | Claude Opus 5.5 | Phi 4 | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1317 | Not measured | Only Claude Opus 5.5 measured |
| Design Arena: agents building mobile apps | 1312 | Not measured | Only Claude Opus 5.5 measured |
| Design Arena: spreadsheets | 1356 | Not measured | Only Claude Opus 5.5 measured |
| LiveBench research | 85.0% | Not measured | Only Claude Opus 5.5 measured |
| LiveBench browser | 80.0% | Not measured | Only Claude Opus 5.5 measured |
| LiveBench long agentic | 85.0% | Not measured | Only Claude Opus 5.5 measured |
| SREBench (Vals AI) | 33.6% | Not measured | Only Claude Opus 5.5 measured |
| Finance Agent (Vals AI) | 58.6% | Not measured | Only Claude Opus 5.5 measured |
| Tax Agent Bench (Vals AI) | 45.6% | Not measured | Only Claude Opus 5.5 measured |
| Legal Research Bench (Vals AI) | 50.5% | Not measured | Only Claude Opus 5.5 measured |
| Harvey's Legal Agent Benchmark (Vals AI) | 9.2% | Not measured | Only Claude Opus 5.5 measured |
| Excel Modeling Benchmark (Vals AI) | 75.9% | Not measured | Only Claude Opus 5.5 measured |
| BioMysteryBench (Vals AI) | 79.3% | Not measured | Only Claude Opus 5.5 measured |
| Terminal-Bench-Science (Vals AI) | 47.1% | Not measured | Only Claude Opus 5.5 measured |
| Vals Science Index | 58.7% | Not measured | Only Claude Opus 5.5 measured |
| Time Horizon Index (Vals AI) | 91.3% | Not measured | Only Claude Opus 5.5 measured |
| CUA-bench (Vals AI) | 14.0% | Not measured | Only Claude Opus 5.5 measured |
| Robo-bench (Vals AI) | 14.6% | Not measured | Only Claude Opus 5.5 measured |
| τ²-Bench Telecom | Not measured | 0.0% | Only Phi 4 measured |
| APEX-Agents | 73.5% | Not measured | Only Claude Opus 5.5 measured |
| Remote Labor Index | 21.3% | Not measured | Only Claude Opus 5.5 measured |
| BALROG | Not measured | 11.6% | Only Phi 4 measured |
| SpireClimb | 3.3% | Not measured | Only Claude Opus 5.5 measured |
| Vending-Bench 2 | $9,235 | Not measured | Only Claude Opus 5.5 measured |
| LMArena Search | 1213 | Not measured | Only Claude Opus 5.5 measured |
| Neither model has a result on the other 14 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Claude Opus 5.5 | Phi 4 | Leader |
|---|---|---|---|
| LiveBench reasoning | 92.2% | Not measured | Only Claude Opus 5.5 measured |
| MysteryMechanism (Vals AI) | 49.5% | Not measured | Only Claude Opus 5.5 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 57.5% | Only Phi 4 measured |
| Humanity's Last Exam (Artificial Analysis run) | 61.4% | 3.8% | Claude Opus 5.5 |
| GPQA Diamond (Epoch AI run) | 90.6% | 56.1% | Claude Opus 5.5 |
| ARC-AGI | 98.5% | Not measured | Only Claude Opus 5.5 measured |
| ARC-AGI-2 | 93.3% | Not measured | Only Claude Opus 5.5 measured |
| Chess puzzles | 67.0% | Not measured | Only Claude Opus 5.5 measured |
| Mystery game puzzles | 71.0% | Not measured | Only Claude Opus 5.5 measured |
| EBR-bench | 71.4% | Not measured | Only Claude Opus 5.5 measured |
| LMArena Text: hard prompts | 1536 | 1220 | Claude Opus 5.5 |
| LMArena Text: expert | 1549 | 1203 | Claude Opus 5.5 |
| LMArena Text: hard prompts in English | 1535 | 1230 | Claude Opus 5.5 |
| LMArena Vision: diagrams | 1345 | Not measured | Only Claude Opus 5.5 measured |
| LMArena Vision: homework | 1362 | Not measured | Only Claude Opus 5.5 measured |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Claude Opus 5.5 | Phi 4 | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 18.0 | Only Phi 4 measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 18.0% | Only Phi 4 measured |
| OTIS Mock AIME | 100.0% | 13.8% | Claude Opus 5.5 |
| FrontierMath, tiers 1 to 3 | 91.2% | Not measured | Only Claude Opus 5.5 measured |
| FrontierMath, tier 4 | 95.0% | Not measured | Only Claude Opus 5.5 measured |
| ProofBench | 100.0% | Not measured | Only Claude Opus 5.5 measured |
| MATH level 5 | Not measured | 64.9% | Only Phi 4 measured |
| LMArena Text: math | 1518 | 1246 | Claude Opus 5.5 |
| LMArena Text: mathematical work | 1516 | 1254 | Claude Opus 5.5 |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Claude Opus 5.5 | Phi 4 | Leader |
|---|---|---|---|
| MedCode (Vals AI) | 49.8% | Not measured | Only Claude Opus 5.5 measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 71.4% | Only Phi 4 measured |
| SimpleQA Verified | 72.2% | Not measured | Only Claude Opus 5.5 measured |
| MMLU | Not measured | 84.8% | Only Phi 4 measured |
| LMArena Text: science | 1524 | 1206 | Claude Opus 5.5 |
| LMArena Text: medicine and healthcare | 1509 | 1202 | Claude Opus 5.5 |
| LMArena Text: legal and government | 1518 | 1241 | Claude Opus 5.5 |
| LMArena Text: business and finance | 1494 | 1199 | Claude Opus 5.5 |
| Neither model has a result on the other 9 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Claude Opus 5.5 | Phi 4 | Leader |
|---|---|---|---|
| Design Arena: websites | 1336 | Not measured | Only Claude Opus 5.5 measured |
| Design Arena: UI components | 1394 | Not measured | Only Claude Opus 5.5 measured |
| Design Arena: game dev | 1457 | Not measured | Only Claude Opus 5.5 measured |
| Design Arena: data viz | 1397 | Not measured | Only Claude Opus 5.5 measured |
| Design Arena: 3D | 1477 | Not measured | Only Claude Opus 5.5 measured |
| Design Arena: all code categories | 1390 | Not measured | Only Claude Opus 5.5 measured |
| Design Arena: SVG | 1333 | Not measured | Only Claude Opus 5.5 measured |
| LiveBench design | 86.9% | Not measured | Only Claude Opus 5.5 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index150
| Benchmark | Claude Opus 5.5 | Phi 4 | Leader |
|---|---|---|---|
| Vals Index | 70.2% | Not measured | Only Claude Opus 5.5 measured |
| LiveBench data analysis | 80.3% | Not measured | Only Claude Opus 5.5 measured |
| Public Benefits Bench (Vals AI) | 70.6% | Not measured | Only Claude Opus 5.5 measured |
| SAGE (Vals AI) | 45.8% | Not measured | Only Claude Opus 5.5 measured |
| MedScribe (Vals AI) | 91.4% | Not measured | Only Claude Opus 5.5 measured |
| IFBench | Not measured | 23.5% | Only Phi 4 measured |
| Long context reasoning (AA-LCR) | 84.7% | 0.0% | Claude Opus 5.5 |
| DTBench | 98.9% | Not measured | Only Claude Opus 5.5 measured |
| LMCA | 68.2% | Not measured | Only Claude Opus 5.5 measured |
| Creative writing (Lech Mazur) | Not measured | 62.6% | Only Phi 4 measured |
| Furniture assembly | 83.3% | Not measured | Only Claude Opus 5.5 measured |
| LMArena Text | 1516 | 1217 | Claude Opus 5.5 |
| LMArena Text: instruction following | 1537 | 1201 | Claude Opus 5.5 |
| LMArena Text: creative writing | 1535 | 1181 | Claude Opus 5.5 |
| LMArena Vision | 1321 | Not measured | Only Claude Opus 5.5 measured |
| LMArena Text: English | 1519 | 1231 | Claude Opus 5.5 |
| LMArena Text: non-English | 1507 | 1197 | Claude Opus 5.5 |
| LMArena Text: Chinese | 1582 | 1212 | Claude Opus 5.5 |
| LMArena Text: German | Not measured | 1222 | Only Phi 4 measured |
| LMArena Text: Japanese | 1534 | 1158 | Claude Opus 5.5 |
| LMArena Text: Korean | Not measured | 1151 | Only Phi 4 measured |
| LMArena Text: French | 1493 | 1224 | Claude Opus 5.5 |
| LMArena Text: Spanish | 1508 | 1234 | Claude Opus 5.5 |
| LMArena Text: Russian | 1517 | 1209 | Claude Opus 5.5 |
| LMArena Text: multi-turn | 1501 | 1206 | Claude Opus 5.5 |
| LMArena Text: longer queries | 1532 | 1217 | Claude Opus 5.5 |
| LMArena Text: writing and language | 1532 | 1198 | Claude Opus 5.5 |
| LMArena Text: entertainment and media | 1515 | 1162 | Claude Opus 5.5 |
| LMArena Vision: English | 1317 | Not measured | Only Claude Opus 5.5 measured |
| LMArena Vision: reading text | 1326 | Not measured | Only Claude Opus 5.5 measured |
| LMArena Vision: creative writing | 1320 | Not measured | Only Claude Opus 5.5 measured |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Opus 5.5 | Phi 4 | 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
Claude Opus 5.5$0.014Fits in one request
Phi 4$0.0001Fits in one request
Phi 4 costs less
Repository review
50K input + 3K output tokens
Claude Opus 5.5$0.260Fits in one request
Phi 4$0.0039Exceeds the context window
Phi 4 costs less
Agent loop
200K input + 10K output tokens
Claude Opus 5.5$1.00Fits in one request
Phi 4$0.015Exceeds the context window
Phi 4 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 5.5 | Microsoft Phi 4 |
|---|---|---|
| Maker | Anthropic | Microsoft |
| Weights | No public weights listed | Open weights |
| Released | September 22, 2026 | January 10, 2025 |
| Context window | 1M | 16K |
| Input $/Mtok | $4.00 | $0.07 |
| Output $/Mtok | $20.00 | $0.14 |
| Coding index | 88.8 | Not benchmarked |
| Independent measurements behind it | 5 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Opus 5.5 better than Phi 4 for coding?
Only Claude Opus 5.5 has a coding score, 88.8 on the Vibe Coding Index; Phi 4 has none, so the two cannot be ranked on coding. Phi 4 has the edge where output tokens cost 142.9x less.
Which is cheaper, Claude Opus 5.5 or Phi 4?
Claude Opus 5.5 costs $4.00 per million input tokens and $20.00 per million output tokens; Phi 4 costs $0.07 and $0.14. Cost per solved task is known for neither of them.
Which has the bigger context window, Claude Opus 5.5 or Phi 4?
Claude Opus 5.5, with 1M tokens against 16K.
How many benchmarks is the Claude Opus 5.5 vs Phi 4 comparison based on?
31 benchmarks have a result for both models as of October 21, 2026. Claude Opus 5.5's coding index rests on 5 independent benchmarks and Phi 4's on 0. Where only one model has a result, the page says so instead of naming a winner.