Salesforce’s 70-B frontier model focused on function-calling & retrieval-augmented generation.
Added Apr 13, 2025
Context Window
128.0K
Max Output
16.4K
Input Price (Auto)
$2.50/1M
Output Price (Auto)
$2.50/1M
Cache Read (Auto)
$1.25/1M
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
9.9
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
40.2%
Better than 18% of models compared
HLE
Humanity's Last Exam
6.1%
Better than 48% of models compared
IFBench
Instruction-following benchmark
27.6%
Better than 11% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
21.9%
Better than 24% of models compared
AA-LCR
Long context reasoning evaluation
11.0%
Better than 24% of models compared
Coding
SciCode
Python programming for scientific computing
31.3%
Better than 49% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
1.5%
Better than 16% of models compared
LiveCodeBench
Contamination-free coding benchmark
26.6%
Better than 28% of models compared
Math
AIME 2025
American Invitational Mathematics Examination 2025
53.7%
Better than 51% of models compared
AIME
American Invitational Mathematics Examination
67.0%
Better than 76% of models compared
Math-500
Diverse mathematical problem solving benchmark
93.5%
Better than 74% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
79.5%
Better than 65% of models compared
Last updated Jun 28, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Llama-xLAM-2 70B fc-r with similar models from the same provider or model family.
Llama 3.3 70B Instruct abliterated
huihui-ai/Llama-3.3-70B-Instruct-abliteratedAn abliterated (removed restrictions and censorship) version of Llama 3.3 70b.
Llama 3.1 70B Dracarys 2
abacusai/Dracarys-72B-InstructLlama 3.1 70b finetune that offers improvements on coding.
EVA Llama 3.33 70B
EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0A RP/storywriting specialist model, full-parameter finetune of Llama-3.3-70B-Instruct on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and flavor of the resulting model.
Llama 3 70B abliterated
failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5An abliterated (removed restrictions and censorship) version of Llama 3.1 70b.
Llama 3.3 70B
TEE/llama3-3-70bMeta's Llama 3.3 with 70B parameters. TEE-backed inference with provider attestation support.
Llama 3.3 70b Instruct
meta-llama/llama-3.3-70b-instructLlama 3.3 is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.