Scale Labs SEAL Japanese (SEAL Japanese)
We show this table for reference; we do not rank on it.
Scale's SEAL leaderboard for Japanese: expert raters judge how well models answer about 1,000 prompts written by native Japanese speakers. BenchLM shows it as display-only reference data, excluded from rankings. Scale marked this board deprecated as of March 2025 and no longer adds models.
Rating on SEAL Japanese — November 12, 2026 snapshot
We mirror the published rating view for SEAL Japanese. o1-preview leads the public snapshot at 1118, followed by Gemini 2.0 Pro (December 2024) (1117) and o3-mini (1104). We do not use these results to rank models overall.
o1-preview
OpenAI
Gemini 2.0 Pro (December 2024)
o3-mini
OpenAI
17 modelsCross-domainCurrentDisplay onlyUpdated November 12, 2026 snapshot
Rating table (17 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | o1-previewOpenAI | 1118 | Not reported | Closed |
| 2 | Gemini 2.0 Pro (December 2024)Google | 1117 | Not reported | Unknown |
| 3 | o3-miniOpenAI | 1104 | Not reported | Closed |
| 4 | Gemini 1.5 Pro (August 27, 2024)Google | 1093 | Not reported | Unknown |
| 5 | o1 (December 2024)OpenAI | 1086 | Not reported | Unknown |
| 6 | Gemini 1.5 Pro (November 2024)Google | 1084 | Not reported | Unknown |
| 7 | GPT-4o (August 2024)OpenAI | 1077 | Not reported | Unknown |
| 8 | Claude 3.5 Sonnet (June 2024)Anthropic | 1069 | Not reported | Unknown |
| 9 | Gemini Pro Flash 2Google | 1064 | Not reported | Unknown |
| 10 | GPT-4 (November 2024)OpenAI | 978 | Not reported | Unknown |
| 11 | Mistral Large 2Mistral | 967 | Not reported | Closed |
| 12 | Gemini 1.5 FlashGoogle | 966 | Not reported | Closed |
| 13 | Aya Expanse 32BCohere | 960 | Not reported | Unknown |
| 14 | Llama 3.1 405B InstructMeta | 895 | Not reported | Unknown |
| 15 | Gemma 2 27BGoogle | 892 | Not reported | Open |
| 16 | Llama 3.3 70B InstructMeta | 778 | Not reported | Unknown |
| 17 | Aya 23 35B*Cohere | 760 | Not reported | Unknown |
How to read this leaderboard
Compare the published configurations as complete evaluation systems. The source can combine a base model, agent scaffold, tools, budget, and inference setting in each result.
Operator receipt: 17 sourced rows are currently displayable on this page; the leading published row is o1-preview at 1118.
Honest limit: This Scale table is display-only context, not benchmark provenance or a weighted model-only comparison. Scale marked this board deprecated as of March 2025 and no longer adds models.
How BenchLM shows SEAL Japanese
BenchLM mirrors 17 published rows from Scale Labs’ public SEAL Japanese leaderboard, captured on November 12, 2026 snapshot.
The table is display only. It is useful context for a published agent or model configuration, but it does not enter BenchLM’s overall or category rankings. Scale marked this board deprecated as of March 2025 and no longer adds models.
Snapshot
The published SEAL Japanese snapshot places o1-preview first at 1118. The third row is 14 score units behind. The broader top-10 range is 140 score units, so the table still separates the published systems.
17 models have been evaluated on SEAL Japanese. The benchmark falls in the Cross-domain category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. SEAL Japanese is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About SEAL Japanese
Year
2026
Tasks
About 1,000 prompts per language
Format
Elo-style rating
Difficulty
External agent and model evaluation
Single-turn prompts across general and culturally specific scenarios, rated by native-speaking experts. Scores are ratings on an Elo-style scale built from expert human comparisons, so only the gaps between rows carry meaning. BenchLM mirrors 17 published rows captured on November 12, 2026 snapshot.
Freshness and provenance
Version
SEAL Japanese 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does SEAL Japanese measure?
Scale's SEAL leaderboard for Japanese: expert raters judge how well models answer about 1,000 prompts written by native Japanese speakers. BenchLM shows it as display-only reference data, excluded from rankings. Scale marked this board deprecated as of March 2025 and no longer adds models.
Which model leads the published SEAL Japanese snapshot?
o1-preview currently leads the published SEAL Japanese snapshot with 1118 rating. BenchLM shows this benchmark for display only and does not use it in overall rankings.
How many models are evaluated on SEAL Japanese?
The November 12, 2026 snapshot snapshot contains 17 AI models.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.