SmolLM2 1.7B Instruct
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsSmolLM2 1.7B Instruct
Model evaluation
Capability & preference
Human preference · Arena
Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.
Recorded results
Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.
Arena text preference / codinghuman preference · 2026-10-28 · rating
SmolLM2 1.7B Instruct
1,047.55 rating
Confidence interval: 1,015.66 – 1,079.45
352 votes
- Category
- coding
- Evaluated configuration
- SmolLM2 1.7B Instruct
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
SmolLM2 1.7B Instruct
1,031.13 rating
Confidence interval: 997.05 – 1,065.21
341 votes
- Category
- creative_writing
- Evaluated configuration
- SmolLM2 1.7B Instruct
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
SmolLM2 1.7B Instruct
1,092.64 rating
Confidence interval: 1,074.00 – 1,111.27
1111 votes
- Category
- english
- Evaluated configuration
- SmolLM2 1.7B Instruct
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
SmolLM2 1.7B Instruct
796.92 rating
Confidence interval: 766.01 – 827.84
1601 votes
- Category
- exclude_ties
- Evaluated configuration
- SmolLM2 1.7B Instruct
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
SmolLM2 1.7B Instruct
1,052.97 rating
Confidence interval: 1,028.98 – 1,076.95
572 votes
- Category
- hard_prompts
- Evaluated configuration
- SmolLM2 1.7B Instruct
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
SmolLM2 1.7B Instruct
1,068.35 rating
Confidence interval: 1,037.10 – 1,099.60
334 votes
- Category
- hard_prompts_english
- Evaluated configuration
- SmolLM2 1.7B Instruct
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
SmolLM2 1.7B Instruct
965.16 rating
Confidence interval: 922.25 – 1,008.08
252 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- SmolLM2 1.7B Instruct
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
SmolLM2 1.7B Instruct
1,007.58 rating
Confidence interval: 975.32 – 1,039.85
360 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- SmolLM2 1.7B Instruct
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
SmolLM2 1.7B Instruct
1,046.16 rating
Confidence interval: 1,011.78 – 1,080.54
352 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- SmolLM2 1.7B Instruct
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
SmolLM2 1.7B Instruct
1,121.99 rating
Confidence interval: 1,088.23 – 1,155.74
240 votes
- Category
- industry_mathematical
- Evaluated configuration
- SmolLM2 1.7B Instruct
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
SmolLM2 1.7B Instruct
1,046.49 rating
Confidence interval: 1,020.66 – 1,072.32
576 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- SmolLM2 1.7B Instruct
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
SmolLM2 1.7B Instruct
1,024.46 rating
Confidence interval: 998.37 – 1,050.54
627 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- SmolLM2 1.7B Instruct
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
SmolLM2 1.7B Instruct
1,029.04 rating
Confidence interval: 1,008.08 – 1,050.00
859 votes
- Category
- instruction_following
- Evaluated configuration
- SmolLM2 1.7B Instruct
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
SmolLM2 1.7B Instruct
1,056.02 rating
Confidence interval: 1,024.19 – 1,087.86
328 votes
- Category
- longer_query
- Evaluated configuration
- SmolLM2 1.7B Instruct
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
SmolLM2 1.7B Instruct
1,104.74 rating
Confidence interval: 1,071.98 – 1,137.49
271 votes
- Category
- math
- Evaluated configuration
- SmolLM2 1.7B Instruct
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
SmolLM2 1.7B Instruct
992.98 rating
Confidence interval: 955.23 – 1,030.73
339 votes
- Category
- multi_turn
- Evaluated configuration
- SmolLM2 1.7B Instruct
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
SmolLM2 1.7B Instruct
984.70 rating
Confidence interval: 964.86 – 1,004.55
1088 votes
- Category
- non_english
- Evaluated configuration
- SmolLM2 1.7B Instruct
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
SmolLM2 1.7B Instruct
1,042.00 rating
Confidence interval: 1,027.93 – 1,056.07
2199 votes
- Category
- overall
- Evaluated configuration
- SmolLM2 1.7B Instruct
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
SmolLM2 1.7B Instruct
981.07 rating
Confidence interval: 949.99 – 1,012.15
410 votes
- Category
- russian
- Evaluated configuration
- SmolLM2 1.7B Instruct
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Apache 2.0
0 selected Compare 0