Benchmark Almanac

LAMBADA Multilingual (Stable LM 2)

stablelm-3b-4e1t 41.7% tops its leaderboard Gemma 2B 39.8% leads the models we track
Not in model cards

Models predict missing final words in narrative passages translated for the Stable LM 2 evaluation. The harness provides five language configurations.

Made by
Stability AI
Released
February 2024
Kind
Reading in many languages
Level
Everyday
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
Many languages
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Based on
LAMBADA
In views
Many languages
Strongest model tested
Phi-2 #225 on the capability index
Last model added
February 2024
Scores refreshed
November 21st, 2026
12
Entries in its paper, 3 models we track

stablelm-3b-4e1t tops the leaderboard with 41.7% Gemma 2B leads with 39.8% among models released by February 2024

Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Gemma 2B, at 39.8%. This view shows only models we track, each at its best.

The newest model with a score here came out in February 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 stablelm-3b-4e1t 41.7%
  2. 2 stablelm-2-zephyr-1_6b † 41.5%
  3. 3 stablelm-2-1_6b 40.5%
  4. 4 Gemma 2B 39.8%
  5. 5 gemma-2b-it † 38.2%
  6. 6 open_llama_3b 37.5%
  7. 7 Qwen-1.5-1.8B-Chat 35.5%
  8. 8 Qwen-1.5-1.8B 34.8%
  9. 9 TinyLLama-1.1B 34.8%
  10. 10 Phi-2 34.6%
  11. 11 falcon-rw-1b 29.9%
  12. 12 Phi-1.5 29.7%

Source: The LAMBADA Multilingual (Stable LM 2) paper

Source: The LAMBADA Multilingual (Stable LM 2) paper

#EntryScoreSettingDateSource
1 stablelm-3b-4e1t 41.7% Official leaderboard
2 stablelm-2-zephyr-1_6b † 41.5% Official leaderboard
3 stablelm-2-1_6b 40.5% Official leaderboard
4 Gemma 2B 39.8% Feb 2024 Official leaderboard
5 gemma-2b-it † 38.2% Official leaderboard
6 open_llama_3b 37.5% Official leaderboard
7 Qwen-1.5-1.8B-Chat 35.5% Official leaderboard
8 Qwen-1.5-1.8B 34.8% Official leaderboard
9 TinyLLama-1.1B 34.8% Official leaderboard
10 Phi-2 34.6% Dec 2023 Official leaderboard
11 falcon-rw-1b 29.9% Official leaderboard
12 Phi-1.5 29.7% Sep 2023 Official leaderboard
#ModelScoreSettingDateSource
1 Gemma 2B 39.8% Feb 2024 Official leaderboard
2 Phi-2 34.6% Dec 2023 Official leaderboard
3 Phi-1.5 29.7% Sep 2023 Official leaderboard

Rankings by part

We read 7 parts from the benchmark’s paper, each ranking models on one part of the test, such as English, German and Spanish. Gemma 2B leads 6 of them, and Phi-2 leads the other one. Arrows show how far a model moved from its overall rank among the models we track.

English

3 models we track have a score here.

  1. 1 Phi-2 ↑1 55.8%
  2. 2 Gemma 2B ↓1 48.6%
  3. 3 Phi-1.5 47.1%

2 models have held number one in the benchmark’s paper since its release in February 2024

Lab claims count from the day the card came out, independent runs from the model’s release.

Microsoft Google DeepMind
Benchmark paper Not tested since Feb 2024
Gemma 2B 39.8%

Source: The LAMBADA Multilingual (Stable LM 2) paper

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) Gemma 2B Phi-2 Phi-1.5 0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) Gemma 2B Phi-1.5

Source: Official LAMBADA Multilingual (Stable LM 2) leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Multilingual

All 545 in Multilingual
  • MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
  • WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET. K-EXAONE 90.5%
  • MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language. Qwen3.7-Max 87%
  • CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories. Solar Open 2 90.7%
  • Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
  • MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%

Data audit

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in February 2024, for Gemma 2B. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (12 entries).
  • Pass Models scored 3 models we track, plus 9 other entries on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in February 2024, for Gemma 2B.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Phi-2 (#225).
  • Pass Headroom The best is 39.8%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 3 rows for models we track and 9 other entries at the last read.
  • Pass Last read November 21st, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check