# Ultravox v0.6 Llama 3.3 70B Benchmark Scores & Performance

> Ultravox v0.6 Llama 3.3 70B by Fixie AI has 13 source-displayable benchmark rows but no public overall score. It remains unranked.

Canonical page: https://benchlm.ai/models/ultravox-v0-6-llama-3-3-70b

Last updated: September 18, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Fixie AI |
| Source Type | Open Weight |
| Reasoning Type | Non-Reasoning |
| Context Window | N/A |
| Official model card | [Fixie AI model documentation](https://github.com/fixie-ai/ultravox) |
| Overall Score | Coming soon |
| Overall Rank | Unranked |

## Family & Coverage

- Family: Ultravox v0.6 Llama 3.3 70B
- Variant: base
- Benchmarks covered: 13 of 446
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [τ²-bench results](/benchmarks/tau2-bench) | 26.6% |
| [GDPval-AA](/benchmarks/gdpvalaanormalized) | 0.0% |
| [GDPval-AA](/benchmarks/gdpvalaa) | 50 |

## Coding Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA Coding Index](/benchmarks/aacodingindex) | 11.9% |

## Reasoning Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-LCR](/benchmarks/lcr) | 15.7% |
| [CritPt](/benchmarks/critpt) | 0.0% |

## Knowledge Benchmarks

| Benchmark | Score |
|-----------|-------|
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 7.7% |
| [AA-GPQA Diamond](/benchmarks/aagpqadiamond) | 49.8% |
| [AA-HLE](/benchmarks/aahle) | 3.6% |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -54.2% |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 19.0% |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 90.2% |

## Instruction Following Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-IFBench](/benchmarks/aaifbench) | 47.1% |

## Other Fixie AI Models

- [Ultravox GLM-4P6](/models/ultravox-glm-4p6) - Score: not computed
- [Ultravox GLM-4P7](/models/ultravox-glm-4p7) - Score: not computed
- [Ultravox v0.4.1 Llama 3.1 8B](/models/ultravox-v0-4-1-llama-3-1-8b) - Score: not computed
- [Ultravox v0.5 Llama 3.1 8B](/models/ultravox-v0-5-llama-3-1-8b) - Score: not computed
- [Ultravox v0.5 Llama 3.2 1B](/models/ultravox-v0-5-llama-3-2-1b) - Score: not computed
- [Ultravox v0.7](/models/ultravox-v0-7) - Score: not computed