Lara Mini Base Report (base-model protocol) - MBPP+ (3-shot): leaderboard

Harness: lm-evaluation-harness 0.4.14.dev0; task configs unchanged except shots (A4.T17); no chat template; identical prompts/settings/answer extraction for every model (§5.1; Appendix D). Backends: Log-likelihood tasks: HF Transformers backend, fp32 log-softmax. Generative tasks: vLLM, bf16, greedy decoding, 4,096-token context; backends agree within 0.6 points on checked tasks (§5.1; Appendix D). Shots and metrics: Per A4.T17 (e.g. HellaSwag 10-shot acc_norm, MMLU 5-shot, MMLU-Pro 5-shot CoT exact match, GSM8K 5-shot EM, MATH 4-shot Math-Verify, MGSM 8-shot CoT over 11 languages, MBPP/MBPP+ 3-shot pass@1, CRUXEval 2-shot pass@1) (A4.T17). Answer extraction: Stricter parsers for GSM8K, MGSM (native CoT answer phrase) and MBPP+ (must pass MBPP and EvalPlus tests); MATH Minerva prompts with Math-Verify over 5,000 problems; CRUXEval direct prediction with official parser (Appendix D Answer extraction). Evaluated Lara checkpoint: Released checkpoint after the 100B-token long-context stage (translated/Lara-4-Mini-Base @ c998c0e1251a734eeff364d532330790a4f93c65 as captured; revision used by the authors not stated) (§5 introduction; §7 Release). Long context: RULER (13 tasks), ONERULER (4 retrieval tasks, 26 languages), HELMET (4 categories) at 32k and 128k with base-model modifications in A4.T24 (§5.7; Appendix D.3; A4.T24). Runs / seeds: not stated; scoring is log-likelihood or greedy generation (not stated). Benchmark availability: T-HellaSwag is the authors' translation, announced as "will release" at v1 (§5.2; §7). This board: Full benchmark (MATH: 5,000 problems; others not printed); Single greedy generation per item (vLLM bf16, 4,096-token context); run count not stated. lm-evaluation-harness 0.4.14.dev0, 3-shot (A4.T17); answer-extraction overrides in Appendix D. Metric: pass@1; must pass MBPP's own and the EvalPlus tests (%) Higher is better.

Metric: pass@1; must pass MBPP's own and the EvalPlus tests (%). Source: arxiv.org. Saturation forecast: Around February 2027. 55 models tracked. Updated 14 Nov 2026.

Top models

#ModelScoreOverall rank
1Qwen3-8B-Base70.4#1774
2Qwen 2.5 7B68.3#2829
3Qwen3-4B-Base68#2469
4Hunyuan-4B-Pretrain62.4#2455
5Hunyuan-1.8B-Pretrain62.2#5939
6Qwen3-1.7B-Base59.8#5246
7Qwen3.5-4B-Base58.7#2478
8Nemotron-Flash-3B58.7#6435
9Falcon-H1-1.5B-Deep-Base58.5#5677
10granite-4.0-h-tiny-base58.5#5994
11Lara-4-Mini-Base58.2#5152
12Domyn-Edge-Base55.8#4368
13Apertus-v1.5-8B-base55.8#4427
14Falcon-H1-1.5B-Base55.3#6880
15SmolLM3-3B-Base54.5#6586

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=lara-mini-base-report-base-model-protocol-mbpp-plus-3-shot · How It Works · Data refreshed daily, snapshot 2026-11-16.