Claude Haiku 4.5 vs DeepSeek V3.1 Terminus
Claude Haiku 4.5 leads DeepSeek V3.1 Terminus on the Artificial Analysis Intelligence Index, 16.9 to 14.8, and DeepSeek V3.1 Terminus costs 4.9x less per output token ($1.0142 vs $5.00 per million). Updated October 22, 2026; 32 benchmarks have a result for both.
Claude Haiku 4.5 or DeepSeek V3.1 Terminus: which to pick
Only Claude Haiku 4.5 has a coding score, 35.6 on the Vibe Coding Index; DeepSeek V3.1 Terminus has none, so the two cannot be ranked on coding.
Pick DeepSeek V3.1 Terminus for output tokens 4.9x cheaper ($1.0142 vs $5.00 per million) and work measured by LMArena Text: hard prompts or LMArena Text: math, where it leads.
- Shared results
- 32
- Claude Haiku 4.5 only
- 63
- DeepSeek V3.1 Terminus only
- 13
- 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 Haiku 4.5 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Claude Haiku 4.5
Claude Haiku 4.5 leads, 16.9 against 14.8.
Same board, both measured
Agentic work
AA Agentic Index
Claude Haiku 4.5
Claude Haiku 4.5 leads, 8.0 against 6.8.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only Claude Haiku 4.5 has a GPQA Diamond result, 72.2%.
Directional only
Math
AIME
No call
Only Claude Haiku 4.5 has a AIME result, 82.7%.
Directional only
Knowledge
MMLU Pro
No call
Only Claude Haiku 4.5 has a MMLU Pro result, 78.7%.
Directional only
Web design
Design Arena: websites
DeepSeek V3.1 Terminus
DeepSeek V3.1 Terminus leads, 1187 against 1122.
Same board, both measured
Long documents
Listed context window
Claude Haiku 4.5
Claude Haiku 4.5 takes 200K tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3.1 Terminus
Claude Haiku 4.5 $0.0035, DeepSeek V3.1 Terminus $0.0008 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Claude Haiku 4.5 has the number, $0.56.
Directional only
At a glance
- Coding index
- Claude Haiku 4.5 35.6 from 4 benchmarks, DeepSeek V3.1 Terminus not benchmarked.
- Widest category
- Knowledge, 7.9 points apart on average over 4 shared benchmarks.
- Widest single gap
- LMArena Text: Polish: Claude Haiku 4.5 1343 against DeepSeek V3.1 Terminus 1427, 14.0 points apart on a 0 to 100 scale.
- Output price
- Claude Haiku 4.5 $5.00 against DeepSeek V3.1 Terminus $1.0142 per million output tokens, 4.9x apart.
- Context window
- Claude Haiku 4.5 takes 200K tokens, DeepSeek V3.1 Terminus 164K.
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 Haiku 4.5 | Bars | DeepSeek V3.1 Terminus | Ties |
|---|---|---|---|---|
| Coding | 3 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 1 | 1 | ||
| Math | 0 | 1 | ||
| Knowledge | 0 | 4 | ||
| Web design | 0 | 7 | ||
| General | 3 | 10 | ||
| All shared boards | 9 | 23 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
| Benchmark | Claude Haiku 4.5 | DeepSeek V3.1 Terminus | Leader |
|---|---|---|---|
| SWE-bench Verified | 66.6% | Not measured | Only Claude Haiku 4.5 measured |
| SWE-bench Multilingual | 64.7% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench coding | 48.1% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena WebDev | 1330 | Not measured | Only Claude Haiku 4.5 measured |
| AA Coding Index | 43.9 | 43.5 | Claude Haiku 4.5 |
| LiveCodeBench (Vals AI) | 41.2% | Not measured | Only Claude Haiku 4.5 measured |
| SWE-bench Verified (Vals AI) | 66.6% | Not measured | Only Claude Haiku 4.5 measured |
| Vibe Code Bench (Vals AI) | 11.4% | Not measured | Only Claude Haiku 4.5 measured |
| Code migration (Vals AI) | 7.5% | Not measured | Only Claude Haiku 4.5 measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only Claude Haiku 4.5 measured |
| Terminal-Bench 2.1 (Vals AI) | 43.8% | Not measured | Only Claude Haiku 4.5 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 79.8% | Only DeepSeek V3.1 Terminus measured |
| SciCode | Not measured | 38.0% | Only DeepSeek V3.1 Terminus measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 31.8% | Only DeepSeek V3.1 Terminus measured |
| Terminal-Bench | 35.5% | Not measured | Only Claude Haiku 4.5 measured |
| WeirdML | 45.4% | Not measured | Only Claude Haiku 4.5 measured |
| ALE-Bench | Not measured | 745.2 | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: coding | 1454 | 1425 | Claude Haiku 4.5 |
| LMArena Text: software and IT | 1439 | 1426 | Claude Haiku 4.5 |
| LMArena WebDev: React | 1326 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena WebDev: HTML | 1318 | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 18 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Claude Haiku 4.5 | DeepSeek V3.1 Terminus | Leader |
|---|---|---|---|
| AA Intelligence Index | 16.9 | 14.8 | Claude Haiku 4.5 |
| Epoch Capabilities Index | 142.2 | Not measured | Only Claude Haiku 4.5 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Claude Haiku 4.5 | DeepSeek V3.1 Terminus | Leader |
|---|---|---|---|
| AA Agentic Index | 8.0 | 6.8 | Claude Haiku 4.5 |
| LiveBench research | 42.2% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench browser | 40.0% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench long agentic | 11.1% | Not measured | Only Claude Haiku 4.5 measured |
| Finance Agent (Vals AI) | 31.0% | Not measured | Only Claude Haiku 4.5 measured |
| Tax Agent Bench (Vals AI) | 5.9% | Not measured | Only Claude Haiku 4.5 measured |
| Legal Research Bench (Vals AI) | 10.6% | Not measured | Only Claude Haiku 4.5 measured |
| Excel Modeling Benchmark (Vals AI) | 22.7% | Not measured | Only Claude Haiku 4.5 measured |
| τ²-Bench Telecom | Not measured | 37.1% | Only DeepSeek V3.1 Terminus measured |
| BALROG | 31.2% | Not measured | Only Claude Haiku 4.5 measured |
| DeepResearch Bench | 45.5% | Not measured | Only Claude Haiku 4.5 measured |
| Vending-Bench 2 | $459 | Not measured | Only Claude Haiku 4.5 measured |
| Berkeley Function Calling Leaderboard (BFCL) | 68.7% | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 28 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Claude Haiku 4.5 | DeepSeek V3.1 Terminus | Leader |
|---|---|---|---|
| GPQA Diamond | 72.2% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench reasoning | 61.7% | Not measured | Only Claude Haiku 4.5 measured |
| MMMU Pro (Vals AI) | 46.1% | Not measured | Only Claude Haiku 4.5 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 79.2% | Only DeepSeek V3.1 Terminus measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 16.4% | Only DeepSeek V3.1 Terminus measured |
| GPQA Diamond (Epoch AI run) | 71.2% | Not measured | Only Claude Haiku 4.5 measured |
| ARC-AGI | 47.7% | Not measured | Only Claude Haiku 4.5 measured |
| ARC-AGI-2 | 4.0% | Not measured | Only Claude Haiku 4.5 measured |
| Chess puzzles | 8.0% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: hard prompts | 1421 | 1426 | DeepSeek V3.1 Terminus |
| LMArena Text: expert | 1443 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: hard prompts in English | 1435 | 1432 | Claude Haiku 4.5 |
| Kagi LLM Benchmark | Not measured | 57.4% | Only DeepSeek V3.1 Terminus measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Claude Haiku 4.5 | DeepSeek V3.1 Terminus | Leader |
|---|---|---|---|
| AIME | 82.7% | Not measured | Only Claude Haiku 4.5 measured |
| MGSM (Vals AI) | 92.2% | Not measured | Only Claude Haiku 4.5 measured |
| AA Math Index | Not measured | 89.7 | Only DeepSeek V3.1 Terminus measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 89.7% | Only DeepSeek V3.1 Terminus measured |
| OTIS Mock AIME | 66.7% | Not measured | Only Claude Haiku 4.5 measured |
| MATH level 5 | 96.4% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: math | 1398 | 1402 | DeepSeek V3.1 Terminus |
| LMArena Text: mathematical work | 1430 | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 5 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Claude Haiku 4.5 | DeepSeek V3.1 Terminus | Leader |
|---|---|---|---|
| MMLU Pro | 78.7% | Not measured | Only Claude Haiku 4.5 measured |
| LegalBench (Vals AI) | 81.2% | Not measured | Only Claude Haiku 4.5 measured |
| CaseLaw (Vals AI) | 56.5% | Not measured | Only Claude Haiku 4.5 measured |
| CorpFin (Vals AI) | 60.6% | Not measured | Only Claude Haiku 4.5 measured |
| TaxEval (Vals AI) | 67.5% | Not measured | Only Claude Haiku 4.5 measured |
| MortgageTax (Vals AI) | 62.2% | Not measured | Only Claude Haiku 4.5 measured |
| MedQA (Vals AI) | 79.6% | Not measured | Only Claude Haiku 4.5 measured |
| MedCode (Vals AI) | 32.7% | Not measured | Only Claude Haiku 4.5 measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 85.1% | Only DeepSeek V3.1 Terminus measured |
| SimpleQA Verified | 13.2% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: science | 1406 | 1451 | DeepSeek V3.1 Terminus |
| LMArena Text: medicine and healthcare | 1394 | 1468 | DeepSeek V3.1 Terminus |
| LMArena Text: legal and government | 1400 | 1457 | DeepSeek V3.1 Terminus |
| LMArena Text: business and finance | 1400 | 1414 | DeepSeek V3.1 Terminus |
| Neither model has a result on the other 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index07
| Benchmark | Claude Haiku 4.5 | DeepSeek V3.1 Terminus | Leader |
|---|---|---|---|
| Design Arena: websites | 1122 | 1187 | DeepSeek V3.1 Terminus |
| Design Arena: UI components | 1097 | 1182 | DeepSeek V3.1 Terminus |
| Design Arena: game dev | 1097 | 1131 | DeepSeek V3.1 Terminus |
| Design Arena: data viz | 1124 | 1168 | DeepSeek V3.1 Terminus |
| Design Arena: 3D | 1071 | 1141 | DeepSeek V3.1 Terminus |
| Design Arena: all code categories | 1114 | 1175 | DeepSeek V3.1 Terminus |
| Design Arena: SVG | 1025 | 1065 | DeepSeek V3.1 Terminus |
| Design Arena: ASCII art | 1140 | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench design | 59.9% | Not measured | Only Claude Haiku 4.5 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index310
| Benchmark | Claude Haiku 4.5 | DeepSeek V3.1 Terminus | Leader |
|---|---|---|---|
| LiveBench data analysis | 59.3% | Not measured | Only Claude Haiku 4.5 measured |
| Public Benefits Bench (Vals AI) | 54.3% | Not measured | Only Claude Haiku 4.5 measured |
| SAGE (Vals AI) | 31.8% | Not measured | Only Claude Haiku 4.5 measured |
| MedScribe (Vals AI) | 85.2% | Not measured | Only Claude Haiku 4.5 measured |
| Vals Multimodal Index | 42.9% | Not measured | Only Claude Haiku 4.5 measured |
| IFBench | Not measured | 57.0% | Only DeepSeek V3.1 Terminus measured |
| Long context reasoning (AA-LCR) | Not measured | 69.3% | Only DeepSeek V3.1 Terminus measured |
| DTBench | 73.6% | 81.3% | DeepSeek V3.1 Terminus |
| LMCA | 30.9% | 28.6% | Claude Haiku 4.5 |
| ExploitBench | 13.7% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text | 1397 | 1419 | DeepSeek V3.1 Terminus |
| LMArena Text: instruction following | 1414 | 1404 | Claude Haiku 4.5 |
| LMArena Text: creative writing | 1371 | 1403 | DeepSeek V3.1 Terminus |
| LMArena Text: English | 1414 | 1429 | DeepSeek V3.1 Terminus |
| LMArena Text: non-English | 1377 | 1408 | DeepSeek V3.1 Terminus |
| LMArena Text: Chinese | 1418 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: German | 1374 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: Japanese | 1338 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: Korean | 1346 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: French | 1411 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: Spanish | 1421 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: Russian | 1381 | 1435 | DeepSeek V3.1 Terminus |
| LMArena Text: Polish | 1343 | 1427 | DeepSeek V3.1 Terminus |
| LMArena Text: multi-turn | 1409 | 1411 | DeepSeek V3.1 Terminus |
| LMArena Text: longer queries | 1427 | 1422 | Claude Haiku 4.5 |
| LMArena Text: writing and language | 1386 | 1409 | DeepSeek V3.1 Terminus |
| LMArena Text: entertainment and media | 1369 | 1391 | DeepSeek V3.1 Terminus |
| LMArena Document | 1420 | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 18 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Haiku 4.5 | DeepSeek V3.1 Terminus | 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
DeepSeek V3.1 Terminus costs less
Repository review
50K input + 3K output tokens
DeepSeek V3.1 Terminus costs less
Agent loop
200K input + 10K output tokens
DeepSeek V3.1 Terminus 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 Haiku 4.5 | DeepSeek V3.1 Terminus |
|---|---|---|
| Maker | Anthropic | DeepSeek |
| Weights | No public weights listed | Open weights |
| Released | October 15, 2025 | September 22, 2025 |
| Context window | 200K | 164K |
| Input $/Mtok | $1.00 | $0.3063 |
| Output $/Mtok | $5.00 | $1.0142 |
| Coding index | 35.6 | Not benchmarked |
| Independent measurements behind it | 4 | 0 |
| Cost per solved task | $0.56 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Haiku 4.5 better than DeepSeek V3.1 Terminus for coding?
Only Claude Haiku 4.5 has a coding score, 35.6 on the Vibe Coding Index; DeepSeek V3.1 Terminus has none, so the two cannot be ranked on coding. Pick DeepSeek V3.1 Terminus for output tokens 4.9x cheaper ($1.0142 vs $5.00 per million) and work measured by LMArena Text: hard prompts or LMArena Text: math, where it leads.
Which is cheaper, Claude Haiku 4.5 or DeepSeek V3.1 Terminus?
Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; DeepSeek V3.1 Terminus costs $0.3063 and $1.0142. Cost per solved task is known for Claude Haiku 4.5 only.
Which has the bigger context window, Claude Haiku 4.5 or DeepSeek V3.1 Terminus?
Claude Haiku 4.5, with 200K tokens against 164K.
How many benchmarks is the Claude Haiku 4.5 vs DeepSeek V3.1 Terminus comparison based on?
32 benchmarks have a result for both models as of October 22, 2026. Claude Haiku 4.5's coding index rests on 4 independent benchmarks and DeepSeek V3.1 Terminus's on 0. Where only one model has a result, the page says so instead of naming a winner.