IBM
availableShows if the model has enough results for an index.Granite 4.2 8B
Granite 4.2 8B is a reasoning model from IBM in the Granite 4.2 family. 22 benchmarks count toward its score, in 6 categories.
IndexOverall score. 50 is the middle.37.6 ±4.9
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.51/s
Input / 1MUS dollars per 1M input tokens.$0.06
Output / 1MUS dollars per 1M output tokens.$0.25
ContextMaximum tokens in one request.131K
EloLMArena rating and rank.1317 (#225)
50 is the middle of the board. The range shows the doubt in the index.
3,087 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category. 50 is the middle.
50 is the middleResults
22 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result on the index scale. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| American Invitational Mathematics Examination 2025 | Math | 86.7% | 45.1 | — | — | Mathematical Association of America |
| Instruction Following Benchmark | Instruction | 79.3% | 58.4 | — | — | Benchmark authors |
| Harvard-MIT Mathematics Tournament February 2025 | Math | 78.3% | 38.7 | — | — | Qwen |
| Massive Multitask Language Understanding Professional | Knowledge | 74.0% | 37.1 | — | — | Yubo Wang et al. |
| LiveCodeBench v6 | Coding | 73.2% | 43.7 | — | — | LiveCodeBench maintainers |
| Graduate-Level Google-Proof Q&A | Knowledge | 64.1% | 37.5 | — | — | David Rein et al. |
| Artificial Analysis GPQA Diamond | Knowledge | 63.1% | 33.2 | — | — | Artificial Analysis |
| τ³-Bench Tool-Agent-User Evaluation | Agentic | 58.1% | 44.5 | — | — | Sierra Research |
| Berkeley Function Calling Leaderboard v4 | Agentic | 52.4% | 36.9 | — | — | Arcee AI |
| Software Engineering Benchmark Verified | Coding | 47.7% | 35.8 | — | — | Carlos E. Jimenez et al. |
| Artificial Analysis Long Context Reasoning | Reasoning | 45.0% | 39.4 | — | — | Artificial Analysis |
| Scientific Code Benchmark | Coding | 36.1% | 45.7 | — | — | Benchmark authors |
| Artificial Analysis SciCode | Coding | 31.5% | 36.6 | — | — | Artificial Analysis |
| Artificial Analysis Coding Index | Coding | 22.4% | 34.7 | — | — | Artificial Analysis |
| Terminal-Bench 2.1 (provider run) | Agentic | 20.6% | 36.2 | — | — | DeepSeek-AI |
| Terminal-Bench 2.1 (provider run) | Agentic | 20.6% | 36.2 | — | — | DeepSeek-AI |
| SWE-bench Pro | Coding | 19.1% | 22.4 | — | — | Xiang Deng et al. |
| Artificial Analysis Omniscience Accuracy | Knowledge | 11.2% | 27.7 | — | — | Artificial Analysis |
| Artificial Analysis Intelligence Index | Knowledge | 11.1% | 36.2 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 9.7% | 35.1 | — | — | Artificial Analysis |
| Artificial Analysis Agentic Index | Agentic | 3.7% | 40.2 | — | — | Artificial Analysis |
| Critical Physics Tasks | Reasoning | 0.3% | 39.0 | — | — | Artificial Analysis |
| GDPval-AA normalized | Agentic | 0.0% | 35.6 | — | — | Artificial Analysis |
22 benchmarks count, from 23 of 23 results. A grey row does not count. Too few models took that benchmark.