Codesota · Models · granite-3.1-3b-a800m-instructibm-granite8 results · 1 benchmarks
Model card

granite-3.1-3b-a800m-instruct.

ibm-graniteopen-source
§ 01 · Benchmarks

Every benchmark granite-3.1-3b-a800m-instruct has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaleq-bench23.9%#166/299—source ↗
02Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolemo2-in65.1%#411/490—source ↗
03Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaldyk28.9%#430/489—source ↗
04Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalbelebele36.1%#441/490—source ↗
05Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalaverage13.7%#448/491—source ↗
06Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolqa-open-book52.2%#468/489—source ↗
07Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalcbd11.6%#487/490—source ↗
08Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalppc5.2%#488/490—source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area

Where granite-3.1-3b-a800m-instruct actually performs.

Natural Language Processing
1
benchmark
avg rank #417.4
§ 04 · Related models

Other ibm-granite models scored on Codesota.

granite-3.0-2b-base
0 results
granite-3.0-2b-instruct
0 results
granite-3.0-8b-instruct
0 results
granite-3.1-1b-a400m-instruct
0 results
granite-3.1-2b-instruct
2.53B params · 0 results
granite-3.1-3b-a800m-base
0 results
granite-3.1-8b-instruct
0 results
§ 05 · Sources & freshness

Where these numbers come from.

speakleash/open_pl_llm_leaderboard
8
results
8 of 8 rows marked verified.