Snowflake: arctic-instruct
2 benchmarks
Leaderboard position
#1021
Overall rank (of 1122 models)
-183
Elo rating
2
Benchmarks
Top 91.0%
Percentile
In Snowflake (of 3 models)
Above: Whisper Distillation: distil-large-v2 #1020
Below: Stability AI: stable-diffusion-3.5-large-turbo #1022
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 |
|---|---|---|
| Google: palm-2 | 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 | ~68.42 | 50% | — |
| AIME 2025 | ~32.05 | 50% | — |
| AIME 2026 | ~53.47 | 50% | — |
| HMMT Feb 2026 | ~44.86 | 50% | — |
| GPQA Diamond | ~35.28 | 50% | — |
| MMLU-Pro | ~35.8 | 50% | — |
| Humanity's Last Exam (no tools) | ~4 | 50% | — |
| IFEval | ~68.13 | 50% | — |
| IFBench | ~36.19 | 50% | — |
| HumanEval | ~43.64 | 50% | — |
| MBPP | ~37.65 | 50% | — |
| Terminal-Bench v2.1 | ~8.6 | 50% | — |
| MMLU | ~40.98 | 50% | — |
| SWE-bench Verified | ~6.92 | 50% | — |
| SWE-bench Pro | ~5.24 | 50% | — |
| SciCode | ~10.6 | 50% | — |
| AA-LCR | ~22.74 | 50% | — |
| Humanity's Last Exam (with tools) | ~11.9 | 50% | — |
| GSM8K | ~43.86 | 50% | — |
| -(CoderPPL) | ~-7.34 | 50% | — |
| LiveCodeBench v6 | ~32.26 | 50% | — |
| MMMU-Pro | ~33.46 | 50% | — |
| MATH | ~17.29 | 50% | — |
| BBH | ~42.34 | 50% | — |