ArmBench-LLM v2 - Generation: leaderboard
ArmBench-LLM 5-category edition Generation score: mean BLEU across Armenian email summarization, conversation summarization, paraphrase and English-Armenian short-text translation. 0-100 BLEU, higher is better.
Metric: BLEU (0-100). Source: huggingface.co. Saturation forecast: Around 2034. 32 models tracked. Updated 22 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Ayb-0.5-9B | 27 | |
| 2 | Ayb-0.5-4B | 24.85 | |
| 3 | Gemini 2.5 Flash | 18.95 | #466 |
| 4 | Ayb-0.5-0.8B | 18.92 | |
| 5 | Claude Sonnet 4 | 18.7 | #414 |
| 6 | Gemma 4 31B (IT) | 17.71 | #354 |
| 7 | Claude 3.7 Sonnet | 17.32 | #455 |
| 8 | GPT-5.4 Mini | 16.99 | #409 |
| 9 | Gemini 3 Flash (Preview) | 16.32 | #156 |
| 10 | Grok 4.1 Fast | 15.64 | #431 |
| 11 | GPT-5.2 Pro | 15.6 | #139 |
| 12 | GPT-5.4 Nano | 15.25 | #653 |
| 13 | GPT-6.1 Sol | 15.2 | #15 |
| 14 | DeepSeek V4.1 Flash | 15.08 | #69 |
| 15 | Grok 4 Fast | 14.73 | #446 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=armbench-llm-v2-generation · How It Works · Data refreshed daily, snapshot 2026-11-22.