IBM
availableShows if the model has enough results for an index.Granite 4.2 3B
Granite 4.2 3B is a reasoning model from IBM in the Granite 4.2 family. 17 benchmarks count toward its score, in 6 categories.
IndexOverall score out of 100.32.8 ±5.4
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.—
Input / 1MUS dollars per 1M input tokens.Free
Output / 1MUS dollars per 1M output tokens.Free
ContextMaximum tokens in one request.128K
EloLMArena rating and rank.1297 (#238)
The index is a score out of 100. The ± range shows how much it can change.
3,072 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category, out of 100.
Out of 100Results
17 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result as a score out of 100. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| American Invitational Mathematics Examination 2025 | Math | 78.3% | 38.8 | — | — | Mathematical Association of America |
| Instruction Following Benchmark | Instruction | 74.3% | 52.5 | — | — | Benchmark authors |
| LiveCodeBench v6 | Coding | 69.7% | 40.5 | — | — | LiveCodeBench maintainers |
| Massive Multitask Language Understanding Professional | Knowledge | 67.8% | 27.3 | — | — | Yubo Wang et al. |
| Harvard-MIT Mathematics Tournament February 2025 | Math | 66.7% | 28.3 | — | — | Qwen |
| Artificial Analysis GPQA Diamond | Knowledge | 55.9% | 25.8 | — | — | Artificial Analysis |
| Graduate-Level Google-Proof Q&A | Knowledge | 54.8% | 28.8 | — | — | David Rein et al. |
| Berkeley Function Calling Leaderboard v4 | Agentic | 52.4% | 36.9 | — | — | Arcee AI |
| τ³-Bench Tool-Agent-User Evaluation | Agentic | 45.8% | 34.1 | — | — | Sierra Research |
| Artificial Analysis SciCode | Coding | 25.3% | 28.0 | — | — | Artificial Analysis |
| Artificial Analysis Long Context Reasoning | Reasoning | 24.3% | 25.1 | — | — | Artificial Analysis |
| Scientific Code Benchmark | Coding | 24.1% | 33.0 | — | — | Benchmark authors |
| Artificial Analysis Omniscience Accuracy | Knowledge | 9.2% | 25.3 | — | — | Artificial Analysis |
| Artificial Analysis Intelligence Index | Knowledge | 9.1% | 33.7 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 6.6% | 31.7 | — | — | Artificial Analysis |
| GDPval-AA normalized | Agentic | 0.0% | 35.6 | — | — | Artificial Analysis |
| Critical Physics Tasks | Reasoning | 0.0% | 38.4 | — | — | Artificial Analysis |
17 benchmarks count, from 17 of 17 results. A grey row does not count. Too few models took that benchmark.