Claude Haiku 5.5 vs Llama 3.1 8B Instruct
Claude Haiku 5.5 leads Llama 3.1 8B Instruct on the Artificial Analysis Intelligence Index, 43.4 to 6.9, and Llama 3.1 8B Instruct costs 6.3x less per output token ($0.08 vs $0.50 per million). Updated October 22, 2026; 8 benchmarks have a result for both.
vs boards won of 8 shared
Claude Haiku 5.5 or Llama 3.1 8B Instruct: which to pick
Only Claude Haiku 5.5 has a coding score, 70.7 on the Vibe Coding Index; Llama 3.1 8B Instruct has none, so the two cannot be ranked on coding.
Pick Llama 3.1 8B Instruct for output tokens 6.3x cheaper ($0.08 vs $0.50 per million).
Model AClaude Haiku 5.5Anthropic70.7/1005 independent benchmarksNo cost per solved taskModel BLlama 3.1 8B InstructMeta LlamaNot benchmarkedNo coding benchmarkNo cost per solved task
- Shared results
- 8
- Claude Haiku 5.5 only
- 55
- Llama 3.1 8B Instruct only
- 43
- Like-for-like categories
- 4 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 5.5 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Claude Haiku 5.5
Claude Haiku 5.5 leads, 43.4 against 6.9.
Same board, both measured
Web design
Design Arena: websites
No call
Only Claude Haiku 5.5 has a Design Arena: websites result, 1262.
Directional only
General
Vals Index
No call
Only Claude Haiku 5.5 has a Vals Index result, 58.7%.
Directional only
Long documents
Listed context window
Claude Haiku 5.5
Claude Haiku 5.5 takes 1M tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Llama 3.1 8B Instruct
Claude Haiku 5.5 $0.0003, Llama 3.1 8B Instruct $0.0001 per turn.
List prices
At a glance
- Coding index
- Claude Haiku 5.5 70.7 from 5 benchmarks, Llama 3.1 8B Instruct not benchmarked.
- Widest category
- Math, 97.2 points apart on average over 1 shared benchmark.
- Widest single gap
- OTIS Mock AIME: Claude Haiku 5.5 98.9% against Llama 3.1 8B Instruct 1.7%, 97.2 points apart on a 0 to 100 scale.
- Output price
- Claude Haiku 5.5 $0.50 against Llama 3.1 8B Instruct $0.08 per million output tokens, 6.3x apart.
- Context window
- Claude Haiku 5.5 takes 1M tokens, Llama 3.1 8B Instruct 131K.
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 5.5 | Bars | Llama 3.1 8B Instruct | Ties |
|---|---|---|---|---|
| Intelligence | 2 | 0 | ||
| Reasoning | 2 | 0 | ||
| Math | 1 | 0 | ||
| General | 3 | 0 | ||
| All shared boards | 8 | 0 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index22 boards, none shared
| Benchmark | Claude Haiku 5.5 | Llama 3.1 8B Instruct | Leader |
|---|---|---|---|
| LiveBench coding | 91.4% | Not measured | Only Claude Haiku 5.5 measured |
| LMArena WebDev | 1586 | Not measured | Only Claude Haiku 5.5 measured |
| AA Coding Index | Not measured | 5.4 | Only Llama 3.1 8B Instruct measured |
| Terminal-Bench 4 (Vals AI) | 36.4% | Not measured | Only Claude Haiku 5.5 measured |
| Vibe Code Bench (Vals AI) | 90.4% | Not measured | Only Claude Haiku 5.5 measured |
| Code migration (Vals AI) | 44.6% | Not measured | Only Claude Haiku 5.5 measured |
| ProgramBench (Vals AI) | 2.5% | Not measured | Only Claude Haiku 5.5 measured |
| IOI (Vals AI) | 47.3% | Not measured | Only Claude Haiku 5.5 measured |
| SWE-bench Multimodal (Vals AI) | 44.0% | Not measured | Only Claude Haiku 5.5 measured |
| Vibe Code Bench 1-100 (Vals AI) | 20.4% | Not measured | Only Claude Haiku 5.5 measured |
| CyberBench (Vals AI) | 75.5% | Not measured | Only Claude Haiku 5.5 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 11.6% | Only Llama 3.1 8B Instruct measured |
| SciCode | 55.0% | Not measured | Only Claude Haiku 5.5 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 0.8% | Only Llama 3.1 8B Instruct measured |
| FrontierCode | 46.4% | Not measured | Only Claude Haiku 5.5 measured |
| FrontierSWE | 43.8% | Not measured | Only Claude Haiku 5.5 measured |
| WeirdML | Not measured | 1.7% | Only Llama 3.1 8B Instruct measured |
| LMArena Text: coding | Not measured | 1195 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: software and IT | Not measured | 1195 | Only Llama 3.1 8B Instruct measured |
| LMArena WebDev: React | 1605 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena WebDev: HTML | 1569 | Not measured | Only Claude Haiku 5.5 measured |
| SciCode | 9.2% | Not measured | Only Claude Haiku 5.5 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 Haiku 5.5 | Llama 3.1 8B Instruct | Leader |
|---|---|---|---|
| AA Intelligence Index | 43.4 | 6.9 | Claude Haiku 5.5 |
| Epoch Capabilities Index | 159.3 | 116.5 | Claude Haiku 5.5 |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index17 boards, none shared
| Benchmark | Claude Haiku 5.5 | Llama 3.1 8B Instruct | Leader |
|---|---|---|---|
| LiveBench research | 81.9% | Not measured | Only Claude Haiku 5.5 measured |
| LiveBench browser | 80.0% | Not measured | Only Claude Haiku 5.5 measured |
| LiveBench long agentic | 57.6% | Not measured | Only Claude Haiku 5.5 measured |
| SREBench (Vals AI) | 5.7% | Not measured | Only Claude Haiku 5.5 measured |
| Finance Agent (Vals AI) | 54.1% | Not measured | Only Claude Haiku 5.5 measured |
| Tax Agent Bench (Vals AI) | 31.9% | Not measured | Only Claude Haiku 5.5 measured |
| Legal Research Bench (Vals AI) | 43.3% | Not measured | Only Claude Haiku 5.5 measured |
| Harvey's Legal Agent Benchmark (Vals AI) | 4.2% | Not measured | Only Claude Haiku 5.5 measured |
| Excel Modeling Benchmark (Vals AI) | 59.0% | Not measured | Only Claude Haiku 5.5 measured |
| BioMysteryBench (Vals AI) | 70.4% | Not measured | Only Claude Haiku 5.5 measured |
| Terminal-Bench-Science (Vals AI) | 10.0% | Not measured | Only Claude Haiku 5.5 measured |
| Vals Science Index | 38.5% | Not measured | Only Claude Haiku 5.5 measured |
| τ²-Bench Telecom | Not measured | 16.4% | Only Llama 3.1 8B Instruct measured |
| APEX-Agents | 56.1% | Not measured | Only Claude Haiku 5.5 measured |
| BALROG | Not measured | 15.1% | Only Llama 3.1 8B Instruct measured |
| Vending-Bench 2 | $3,602 | Not measured | Only Claude Haiku 5.5 measured |
| Berkeley Function Calling Leaderboard (BFCL) | Not measured | 25.8% | Only Llama 3.1 8B Instruct measured |
| Neither model has a result on the other 24 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Haiku 5.5 | Llama 3.1 8B Instruct | Leader |
|---|---|---|---|
| LiveBench reasoning | 82.4% | Not measured | Only Claude Haiku 5.5 measured |
| MysteryMechanism (Vals AI) | 35.1% | Not measured | Only Claude Haiku 5.5 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 25.9% | Only Llama 3.1 8B Instruct measured |
| Humanity's Last Exam (Artificial Analysis run) | 44.4% | 5.3% | Claude Haiku 5.5 |
| GPQA Diamond (Epoch AI run) | 89.6% | 27.0% | Claude Haiku 5.5 |
| ARC-AGI | 89.0% | Not measured | Only Claude Haiku 5.5 measured |
| ARC-AGI-2 | 61.3% | Not measured | Only Claude Haiku 5.5 measured |
| Chess puzzles | 55.0% | Not measured | Only Claude Haiku 5.5 measured |
| Mystery game puzzles | 30.0% | Not measured | Only Claude Haiku 5.5 measured |
| EBR-bench | 43.8% | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: hard prompts | Not measured | 1175 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: expert | Not measured | 1144 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: hard prompts in English | Not measured | 1196 | Only Llama 3.1 8B Instruct measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Claude Haiku 5.5 | Llama 3.1 8B Instruct | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 4.3 | Only Llama 3.1 8B Instruct measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 4.3% | Only Llama 3.1 8B Instruct measured |
| OTIS Mock AIME | 98.9% | 1.7% | Claude Haiku 5.5 |
| FrontierMath, tiers 1 to 3 | 75.1% | Not measured | Only Claude Haiku 5.5 measured |
| FrontierMath, tier 4 | 46.3% | Not measured | Only Claude Haiku 5.5 measured |
| ProofBench | 89.0% | Not measured | Only Claude Haiku 5.5 measured |
| MATH level 5 | Not measured | 22.9% | Only Llama 3.1 8B Instruct measured |
| GSM8K | Not measured | 82.4% | Only Llama 3.1 8B Instruct measured |
| LMArena Text: math | Not measured | 1179 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: mathematical work | Not measured | 1180 | Only Llama 3.1 8B Instruct measured |
| Neither model has a result on the other 3 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Claude Haiku 5.5 | Llama 3.1 8B Instruct | Leader |
|---|---|---|---|
| MedCode (Vals AI) | 51.5% | Not measured | Only Claude Haiku 5.5 measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 47.6% | Only Llama 3.1 8B Instruct measured |
| SimpleQA Verified | 23.8% | Not measured | Only Claude Haiku 5.5 measured |
| MMLU | Not measured | 56.1% | Only Llama 3.1 8B Instruct measured |
| LMArena Text: science | Not measured | 1193 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: medicine and healthcare | Not measured | 1182 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: legal and government | Not measured | 1206 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: business and finance | Not measured | 1166 | Only Llama 3.1 8B Instruct measured |
| Neither model has a result on the other 10 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | Claude Haiku 5.5 | Llama 3.1 8B Instruct | Leader |
|---|---|---|---|
| Design Arena: websites | 1262 | Not measured | Only Claude Haiku 5.5 measured |
| Design Arena: UI components | 1291 | Not measured | Only Claude Haiku 5.5 measured |
| Design Arena: game dev | 1313 | Not measured | Only Claude Haiku 5.5 measured |
| Design Arena: data viz | 1294 | Not measured | Only Claude Haiku 5.5 measured |
| Design Arena: 3D | 1342 | Not measured | Only Claude Haiku 5.5 measured |
| Design Arena: all code categories | 1278 | Not measured | Only Claude Haiku 5.5 measured |
| LiveBench design | 83.1% | Not measured | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Claude Haiku 5.5 | Llama 3.1 8B Instruct | Leader |
|---|---|---|---|
| Vals Index | 58.7% | Not measured | Only Claude Haiku 5.5 measured |
| LiveBench data analysis | 53.1% | Not measured | Only Claude Haiku 5.5 measured |
| Public Benefits Bench (Vals AI) | 63.2% | Not measured | Only Claude Haiku 5.5 measured |
| SAGE (Vals AI) | 45.8% | Not measured | Only Claude Haiku 5.5 measured |
| MedScribe (Vals AI) | 89.5% | Not measured | Only Claude Haiku 5.5 measured |
| IFBench | Not measured | 28.6% | Only Llama 3.1 8B Instruct measured |
| Long context reasoning (AA-LCR) | 82.7% | 18.0% | Claude Haiku 5.5 |
| DTBench | 95.0% | 50.9% | Claude Haiku 5.5 |
| LMCA | 51.1% | 5.4% | Claude Haiku 5.5 |
| Furniture assembly | 47.5% | Not measured | Only Claude Haiku 5.5 measured |
| PIQA | Not measured | 81.2% | Only Llama 3.1 8B Instruct measured |
| LMArena Text | Not measured | 1187 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: instruction following | Not measured | 1159 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: creative writing | Not measured | 1154 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: English | Not measured | 1218 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: non-English | Not measured | 1148 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: Chinese | Not measured | 1151 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: German | Not measured | 1144 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: Japanese | Not measured | 1061 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: Korean | Not measured | 1053 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: French | Not measured | 1178 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: Spanish | Not measured | 1169 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: Russian | Not measured | 1158 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: multi-turn | Not measured | 1172 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: longer queries | Not measured | 1181 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: writing and language | Not measured | 1162 | Only Llama 3.1 8B Instruct measured |
| LMArena Text: entertainment and media | Not measured | 1145 | Only Llama 3.1 8B Instruct measured |
| Neither model has a result on the other 19 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Haiku 5.5 | Llama 3.1 8B Instruct | 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 Haiku 5.5$0.0003Fits in one request
Llama 3.1 8B Instruct$0.0001Fits in one request
Llama 3.1 8B Instruct costs less
Repository review
50K input + 3K output tokens
Claude Haiku 5.5$0.0065Fits in one request
Llama 3.1 8B Instruct$0.0027Fits in one request
Llama 3.1 8B Instruct costs less
Agent loop
200K input + 10K output tokens
Claude Haiku 5.5$0.025Fits in one request
Llama 3.1 8B Instruct$0.011Exceeds the context window
Llama 3.1 8B Instruct 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 5.5 | Meta Llama 3.1 8B Instruct |
|---|---|---|
| Maker | Anthropic | Meta Llama |
| Weights | No public weights listed | Open weights |
| Released | October 7, 2026 | July 23, 2024 |
| Context window | 1M | 131K |
| Input $/Mtok | $0.10 | $0.05 |
| Output $/Mtok | $0.50 | $0.08 |
| Coding index | 70.7 | Not benchmarked |
| Independent measurements behind it | 5 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Haiku 5.5 better than Llama 3.1 8B Instruct for coding?
Only Claude Haiku 5.5 has a coding score, 70.7 on the Vibe Coding Index; Llama 3.1 8B Instruct has none, so the two cannot be ranked on coding. Pick Llama 3.1 8B Instruct for output tokens 6.3x cheaper ($0.08 vs $0.50 per million).
Which is cheaper, Claude Haiku 5.5 or Llama 3.1 8B Instruct?
Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens; Llama 3.1 8B Instruct costs $0.05 and $0.08. Cost per solved task is known for neither of them.
Which has the bigger context window, Claude Haiku 5.5 or Llama 3.1 8B Instruct?
Claude Haiku 5.5, with 1M tokens against 131K.
How many benchmarks is the Claude Haiku 5.5 vs Llama 3.1 8B Instruct comparison based on?
8 benchmarks have a result for both models as of October 22, 2026. Claude Haiku 5.5's coding index rests on 5 independent benchmarks and Llama 3.1 8B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.