MetaLlama 3.2 1B
Best configuration ranks #604 of 610 on the BenchLeader Index at 32.6 ±3.1. Last measured 2 Sept 2026. Released 24 Sept 2024.
- Blended price
- $0.071/M
- $0.027 in · $0.201 out
- Output speed
- 58 tok/s
- First answer
- 0.22 s
- Context
- 128k
- Overall index33
- Reasoning22
- Coding25
- Agents & tools28
- Maths24
- Knowledge38
- Instruction following28
- Human preference23
- Long context28
- Composite35
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| GPQA Diamond | 23.9%#265 | Epoch AI Benchmarking Hub |
| LMArena Hard Prompts | 1114#330 | LMArena |
| GPQA Diamond (AA)not in index | 19.6%#522 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 5.5%#353 | Artificial Analysis |
Coding
| Benchmark | default | Source |
|---|---|---|
| LMArena Coding | 1149#325 | LMArena |
Agents & tools
| Benchmark | default | Source |
|---|---|---|
| Terminal-Bench Hard | 0.0%#345 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | 0.0%#375 | Artificial Analysis |
| BFCL Overall | 10.8%#81 | Berkeley Function Calling Leaderboard |
Maths
| Benchmark | default | Source |
|---|---|---|
| OTIS Mock AIME | 0.6%#251 | Epoch AI Benchmarking Hub |
Knowledge
| Benchmark | default | Source |
|---|---|---|
| AA-Omniscience | -54.7#358 | Artificial Analysis |
Instruction following
| Benchmark | default | Source |
|---|---|---|
| IFBench | 22.8%#382 | Artificial Analysis |
Human preference
| Benchmark | default | Source |
|---|---|---|
| LMArena Text | 1111#333 | LMArena |
Long context
| Benchmark | default | Source |
|---|---|---|
| AA-LCR | 6.7%#407 | Artificial Analysis |
Composite
| Benchmark | default | Source |
|---|---|---|
| Epoch Capabilities Indexnot in index | 102.4#208 | Epoch AI Benchmarking Hub |
| AA Intelligence Index | 4.8#527 | Artificial Analysis |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Cloudflare | 58 tok/s | 0.22 s | $0.027 | $0.201 | 60k | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0001 | – | 5.4 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0004 | – | 10.6 s |
| Code edit | 6,000 / 1,500 | $0.0005 | – | 26.1 s |
| Agentic coding session | 60,000 / 4,000 | $0.0024 | – | 1.2 min |
| Structured extraction | 2,000 / 200 | $0.0001 | – | 3.7 s |
See also
Data as of 9 Sept 2026. Compare with another model.