Kimi K2 0905 vs Llama 3.1 8B Instruct
Kimi K2 0905 leads Llama 3.1 8B Instruct on the Artificial Analysis Intelligence Index, 15.3 to 6.9, and Llama 3.1 8B Instruct costs 31.3x less per output token ($0.08 vs $2.50 per million). Updated October 21, 2026; 12 benchmarks have a result for both.
Kimi K2 0905 or Llama 3.1 8B Instruct: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Kimi K2 0905 for a larger context window (262K against 131K tokens).
- Shared results
- 12
- Kimi K2 0905 only
- 5
- Llama 3.1 8B Instruct only
- 39
- Like-for-like categories
- 7 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
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Kimi K2 0905
Kimi K2 0905 leads, 15.3 against 6.9.
Same board, both measured
Web design
Design Arena: websites
No call
Only Kimi K2 0905 has a Design Arena: websites result, 1089.
Directional only
Long documents
Listed context window
Kimi K2 0905
Kimi K2 0905 takes 262K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Llama 3.1 8B Instruct
Kimi K2 0905 $0.0019, Llama 3.1 8B Instruct $0.0001 per turn.
List prices
At a glance
- Coding index
- Kimi K2 0905 not benchmarked, Llama 3.1 8B Instruct not benchmarked.
- Widest category
- Agentic work, 57.0 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: Kimi K2 0905 73.4% against Llama 3.1 8B Instruct 16.4%, 57.0 points apart on a 0 to 100 scale.
- Output price
- Kimi K2 0905 $2.50 against Llama 3.1 8B Instruct $0.08 per million output tokens, 31.3x apart.
- Context window
- Kimi K2 0905 takes 262K 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 | Kimi K2 0905 | Bars | Llama 3.1 8B Instruct | Ties |
|---|---|---|---|---|
| Coding | 3 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 2 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 1 | 0 | ||
| General | 2 | 0 | ||
| All shared boards | 12 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
| Benchmark | Kimi K2 0905 | Llama 3.1 8B Instruct | Leader |
|---|---|---|---|
| AA Coding Index | Not measured | 5.4 | Only Llama 3.1 8B Instruct measured |
| LiveCodeBench (Artificial Analysis run) | 61.0% | 11.6% | Kimi K2 0905 |
| Terminal-Bench Hard (Artificial Analysis run) | 23.5% | 0.8% | Kimi K2 0905 |
| WeirdML | 36.7% | 1.7% | Kimi K2 0905 |
| ALE-Bench | 267.1 | Not measured | Only Kimi K2 0905 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 |
| Neither model has a result on the other 32 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Kimi K2 0905 | Llama 3.1 8B Instruct | Leader |
|---|---|---|---|
| AA Intelligence Index | 15.3 | 6.9 | Kimi K2 0905 |
| Epoch Capabilities Index | Not measured | 116.5 | Only Llama 3.1 8B Instruct measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Kimi K2 0905 | Llama 3.1 8B Instruct | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 73.4% | 16.4% | Kimi K2 0905 |
| BALROG | Not measured | 15.1% | Only Llama 3.1 8B Instruct 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 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Kimi K2 0905 | Llama 3.1 8B Instruct | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 76.7% | 25.9% | Kimi K2 0905 |
| Humanity's Last Exam (Artificial Analysis run) | 6.4% | 5.3% | Kimi K2 0905 |
| GPQA Diamond (Epoch AI run) | Not measured | 27.0% | Only Llama 3.1 8B Instruct 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 |
| Kagi LLM Benchmark | 52.2% | Not measured | Only Kimi K2 0905 measured |
| Neither model has a result on the other 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Kimi K2 0905 | Llama 3.1 8B Instruct | Leader |
|---|---|---|---|
| AA Math Index | 57.3 | 4.3 | Kimi K2 0905 |
| AIME 2025 (Artificial Analysis run) | 57.3% | 4.3% | Kimi K2 0905 |
| OTIS Mock AIME | Not measured | 1.7% | Only Llama 3.1 8B Instruct 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 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Kimi K2 0905 | Llama 3.1 8B Instruct | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 81.9% | 47.6% | Kimi K2 0905 |
| 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 12 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Kimi K2 0905 | Llama 3.1 8B Instruct | Leader |
|---|---|---|---|
| Design Arena: websites | 1089 | Not measured | Only Kimi K2 0905 measured |
| Design Arena: all code categories | 1098 | Not measured | Only Kimi K2 0905 measured |
| Neither model has a result on the other 7 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Kimi K2 0905 | Llama 3.1 8B Instruct | Leader |
|---|---|---|---|
| IFBench | 41.7% | 28.6% | Kimi K2 0905 |
| Long context reasoning (AA-LCR) | 53.0% | 18.0% | Kimi K2 0905 |
| DTBench | Not measured | 50.9% | Only Llama 3.1 8B Instruct measured |
| LMCA | Not measured | 5.4% | Only Llama 3.1 8B Instruct measured |
| Fiction.LiveBench | 66.7% | Not measured | Only Kimi K2 0905 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 24 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Kimi K2 0905 | 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
Llama 3.1 8B Instruct costs less
Repository review
50K input + 3K output tokens
Llama 3.1 8B Instruct costs less
Agent loop
200K input + 10K output tokens
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 | MoonshotAI Kimi K2 0905 | Meta Llama 3.1 8B Instruct |
|---|---|---|
| Maker | Moonshot AI | Meta Llama |
| Weights | Open weights | Open weights |
| Released | September 4, 2025 | July 23, 2024 |
| Context window | 262K | 131K |
| Input $/Mtok | $0.60 | $0.05 |
| Output $/Mtok | $2.50 | $0.08 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Kimi K2 0905 better than Llama 3.1 8B Instruct for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Kimi K2 0905 for a larger context window (262K against 131K tokens).
Which is cheaper, Kimi K2 0905 or Llama 3.1 8B Instruct?
Kimi K2 0905 costs $0.60 per million input tokens and $2.50 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, Kimi K2 0905 or Llama 3.1 8B Instruct?
Kimi K2 0905, with 262K tokens against 131K.
How many benchmarks is the Kimi K2 0905 vs Llama 3.1 8B Instruct comparison based on?
12 benchmarks have a result for both models as of October 21, 2026. Kimi K2 0905's coding index rests on 0 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.