Databricks: DBRX Instruct
2 benchmarks
Leaderboard position
#1050
Overall rank (of 1122 models)
-340
Elo rating
2
Benchmarks
Top 93.6%
Percentile
In Databricks (of 1 models)
Above: OpenChat: openchat-3.5 #1049
Below: LiquidAI: lfm-2.5-350m #1051
Benchmark highlights
Nearest competitor from another company
The model from another company with the most similar benchmark scores.
appeared as nearest in 1 of 2 benchmarks
1/2
50.0%
1/2
50.0%
| Model | Votes | % of benchmarks |
|---|---|---|
| Cohere Labs: c4ai-command-r-plus | 1 | 50.0% |
| Qwen: qwen3-1.7b | 1 | 50.0% |
Benchmarks
Predicted scores
Estimated from 25 similar models and the global Elo rating. These are projections, not measured results.
| Benchmark | Predicted | Confidence | Based on |
|---|---|---|---|
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| MATH-500 | ~65.7 | 50% | — |
| AIME 2025 | ~26.89 | 50% | — |
| AIME 2026 | ~50.44 | 50% | — |
| HMMT Feb 2026 | ~41.8 | 50% | — |
| GPQA Diamond | ~31.82 | 50% | — |
| MMLU-Pro | ~31.94 | 50% | — |
| Humanity's Last Exam (no tools) | ~4 | 50% | — |
| IFEval | ~65.98 | 50% | — |
| IFBench | ~33.59 | 50% | — |
| HumanEval | ~39.09 | 50% | — |
| MBPP | ~31.68 | 50% | — |
| Terminal-Bench v2.1 | ~8.6 | 50% | — |
| MMLU | ~36.93 | 50% | — |
| SWE-bench Verified | ~2.02 | 50% | — |
| SWE-bench Pro | ~5.24 | 50% | — |
| SciCode | ~8.13 | 50% | — |
| AA-LCR | ~19.66 | 50% | — |
| Humanity's Last Exam (with tools) | ~11.9 | 50% | — |
| GSM8K | ~37.96 | 50% | — |
| -(CoderPPL) | ~-8.31 | 50% | — |
| LiveCodeBench v6 | ~28.67 | 50% | — |
| MMMU-Pro | ~30.51 | 50% | — |
| MATH | ~10.7 | 50% | — |
| BBH | ~38.86 | 50% | — |