Quality
Highest overall scores
- 1
IBM: Granite 4.0 Micro0 - 2IBM: Granite 4.1 8B0
IBM model benchmarks.
Compare IBM models across answer quality, coding, complex tasks, speed, price, and context size.
Response speed
Fastest output in this sample
- 1IBM: Granite 4.1 8B114.5 t/s
- 2IBM: Granite 4.0 Micro30 t/s
Input price
Lowest price per 1M tokens
- 1IBM: Granite 4.0 Micro$0.02/1M
- 2IBM: Granite 4.1 8B$0.05/1M
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better
Quality benchmarks
Compare IBM model capability.
Performance and price
Compare practical tradeoffs.
All IBM models.
2 models in the current catalogue.
| Model | Links | |||||
|---|---|---|---|---|---|---|
| IBM: Granite 4.0 Micro | 0 | 30 t/s | 131K | $0.02 | $0.11 | |
| IBM: Granite 4.1 8B | 0 | 114.5 t/s | 131.1K | $0.05 | $0.10 |
IBM technical benchmarks.
Compare named evaluation records available for IBM models. Missing results remain blank rather than being estimated.
| Benchmark | Area | Granite 4.0 Micro | Granite 4.1 8B | Source |
|---|---|---|---|---|
| GPQA | GPQA Diamond | 30.3 | 43.3 | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 5.1 | 3.8 | OpenRouter model benchmarks |
| IFBench | IFBench | 22.1 | 38.6 | OpenRouter model benchmarks |
| τ²-Bench Telecom | τ²-Bench Telecom | 12.6 | 27.8 | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | 4 | 12 | OpenRouter model benchmarks |
| CritPt | CritPt | 0 | 0 | OpenRouter model benchmarks |
| SciCode | SciCode | 11.9 | 21.8 | OpenRouter model benchmarks |
| Terminal-Bench Hard | Terminal-Bench Hard | 1.5 | 0 | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | AA-Omniscience Accuracy | 8.3 | 12.1 | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | 25.5 | 12.7 | OpenRouter model benchmarks |
| Coding Index | coding | — | 9.5 | OpenRouter / artificial-analysis |