GeekRadar / The comparison desk

COMPARE.

AI models

Not reported

INTELLECT-3

Model evaluation

Capability & preference

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

INTELLECT-3 1355.6 INTELLECT-3 · 95% interval 1347.4–1363.8 · 5,435 votes · 2026-10-28

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 / chinesehuman preference · 2026-10-28 · rating

INTELLECT-3

1,353.86 rating

Confidence interval: 1,327.78 – 1,379.94

517 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-28 · rating

INTELLECT-3

1,373.87 rating

Confidence interval: 1,355.68 – 1,392.07

1005 votes

Oct 28, 2026

Category: coding
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

INTELLECT-3

1,315.92 rating

Confidence interval: 1,295.20 – 1,336.64

834 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-28 · rating

INTELLECT-3

1,379.59 rating

Confidence interval: 1,367.76 – 1,391.42

2408 votes

Oct 28, 2026

Category: english
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

INTELLECT-3

1,315.63 rating

Confidence interval: 1,304.01 – 1,327.25

3866 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-28 · rating

INTELLECT-3

1,320.95 rating

Confidence interval: 1,289.40 – 1,352.49

356 votes

Oct 28, 2026

Category: expert
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

INTELLECT-3

1,351.46 rating

Confidence interval: 1,340.36 – 1,362.56

2841 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

INTELLECT-3

1,374.98 rating

Confidence interval: 1,358.82 – 1,391.15

1287 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

INTELLECT-3

1,348.32 rating

Confidence interval: 1,330.00 – 1,366.64

1007 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

INTELLECT-3

1,308.87 rating

Confidence interval: 1,290.81 – 1,326.93

1099 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

INTELLECT-3

1,322.30 rating

Confidence interval: 1,293.73 – 1,350.87

415 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

INTELLECT-3

1,360.88 rating

Confidence interval: 1,341.50 – 1,380.26

920 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

INTELLECT-3

1,366.35 rating

Confidence interval: 1,331.82 – 1,400.88

259 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

INTELLECT-3

1,321.50 rating

Confidence interval: 1,289.55 – 1,353.46

336 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

INTELLECT-3

1,375.75 rating

Confidence interval: 1,361.77 – 1,389.73

1727 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

INTELLECT-3

1,335.41 rating

Confidence interval: 1,319.13 – 1,351.69

1320 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

INTELLECT-3

1,314.79 rating

Confidence interval: 1,299.37 – 1,330.21

1475 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

INTELLECT-3

1,330.67 rating

Confidence interval: 1,314.50 – 1,346.83

1357 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-28 · rating

INTELLECT-3

1,374.79 rating

Confidence interval: 1,344.54 – 1,405.05

343 votes

Oct 28, 2026

Category: math
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

INTELLECT-3

1,350.44 rating

Confidence interval: 1,330.19 – 1,370.69

795 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-28 · rating

INTELLECT-3

1,328.09 rating

Confidence interval: 1,317.34 – 1,338.85

3027 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-28 · rating

INTELLECT-3

1,355.57 rating

Confidence interval: 1,347.38 – 1,363.76

5435 votes

Oct 28, 2026

Category: overall
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-28 · rating

INTELLECT-3

1,348.95 rating

Confidence interval: 1,303.61 – 1,394.28

151 votes

Oct 28, 2026

Category: polish
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-28 · rating

INTELLECT-3

1,338.41 rating

Confidence interval: 1,314.29 – 1,362.54

565 votes

Oct 28, 2026

Category: russian
Evaluated configuration: INTELLECT-3
Evaluation type: human preference

Run it locally

Inference · memory estimate

INTELLECT-3

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: MIT