Qwen3-14B-nonreasoning

# qwen3-14b-reasoning Evaluation Results

## Summary

| Benchmark | Score | Metric | Samples | Overlong rate |
|-----------|-------|--------|---------|---------------|
| aime24 | 0.285 | math_pass@1:64_samples | 64 | 0.0% |
| aime25 | 0.222 | math_pass@1:64_samples | 64 | 0.0% |
| arenahard | 0.796 | eval/overall_winrate | 500 | 0.0% |
| bbh_generative | 0.825 | extractive_match | 1 | 0.0% |
| creative-writing-v3 | 0.516 | creative_writing_score | 96 | 0.0% |
| drop_generative_nous | 0.750 | drop_acc | 1 | 0.0% |
| eqbench3 | 0.697 | eqbench_score | 135 | 0.0% |
| gpqa_diamond | 0.535 | gpqa_pass@1:8_samples | 8 | 0.0% |
| ifeval | 0.921 | inst_level_loose_acc | 1 | 0.0% |
| lcb-v6-aug2024+ | 0.292 | eval/pass_1 | 1 | 0.0% |
| math_500 | 0.885 | math_pass@1:4_samples | 4 | 0.0% |
| mmlu_generative | 0.815 | extractive_match | 1 | 0.0% |
| mmlu_pro | 0.701 | pass@1:1_samples | 1 | 0.0% |
| musr_generative | 0.564 | extractive_match | 1 | 0.0% |
| obqa_generative | 0.940 | extractive_match | 1 | 0.0% |
| rewardbench | 0.667 | eval/percent_correct | 1 | 0.0% |
| simpleqa_nous | 0.047 | fuzzy_match | 1 | 0.0% |

Overlong rate: 0 / 64,523 samples (0.0%) missing closing `</think>` tag

## Detailed Results

### aime24

| Metric | Score | Std Error |
|--------|-------|----------|
| math_pass@1:1_samples | 0.233 | 0.079 |
| math_pass@1:4_samples | 0.275 | 0.071 |
| math_pass@1:8_samples | 0.292 | 0.066 |
| math_pass@1:16_samples | 0.300 | 0.067 |
| math_pass@1:32_samples | 0.296 | 0.068 |
| math_pass@1:64_samples | 0.285 | 0.067 |

**Model:** qwen3-14b-reasoning
**Evaluation Time (hh:mm:ss):** 00:10:23
**Temperature:** 0.6
**Overlong samples:** 0.0% (0 / 1920)

### aime25

| Metric | Score | Std Error |
|--------|-------|----------|
| math_pass@1:1_samples | 0.167 | 0.069 |
| math_pass@1:4_samples | 0.200 | 0.068 |
| math_pass@1:8_samples | 0.221 | 0.067 |
| math_pass@1:16_samples | 0.219 | 0.065 |
| math_pass@1:32_samples | 0.223 | 0.066 |
| math_pass@1:64_samples | 0.222 | 0.065 |

**Model:** qwen3-14b-reasoning
**Evaluation Time (hh:mm:ss):** 00:05:44
**Temperature:** 0.6
**Overlong samples:** 0.0% (0 / 1920)

### arenahard

| Metric | Score | Std Error |
|--------|-------|----------|
| eval/overall_winrate | 0.796 | 0.000 |
| eval/total_samples | 500.000 | 0.000 |
| eval/win_count | 369.000 | 0.000 |
| eval/tie_count | 57.000 | 0.000 |
| eval/loss_count | 74.000 | 0.000 |
| eval/win_rate | 0.738 | 0.000 |
| eval/tie_rate | 0.114 | 0.000 |
| eval/loss_rate | 0.148 | 0.000 |
| eval/winrate_arena-hard-v0.1 | 0.796 | 0.000 |

**Model:** qwen3-14b-nothink-arena
**Evaluation Time (hh:mm:ss):** 00:04:38
**Temperature:** 0.6
**Overlong samples:** 0.0% (0 / 500)

### bbh_generative

| Metric | Score | Std Error |
|--------|-------|----------|
| extractive_match | 0.825 | 0.020 |

**Model:** qwen3-14b-reasoning
**Evaluation Time (hh:mm:ss):** 00:21:48
**Temperature:** 0.6
**Overlong samples:** 0.0% (0 / 5511)

### creative-writing-v3

| Metric | Score | Std Error |
|--------|-------|----------|
| creative_writing_score | 0.516 | 0.000 |
| num_samples | 96.000 | 0.000 |

**Model:** qwen3-14b-nonreasoning
**Evaluation Time (hh:mm:ss):** N/A
**Temperature:** N/A
**Overlong samples:** 0.0% (0 / 96)

### drop_generative_nous

| Metric | Score | Std Error |
|--------|-------|----------|
| drop_acc | 0.750 | 0.004 |

**Model:** qwen3-14b-reasoning
**Evaluation Time (hh:mm:ss):** 00:37:30
**Temperature:** 0.6
**Overlong samples:** 0.0% (0 / 9536)

### eqbench3

| Metric | Score | Std Error |
|--------|-------|----------|
| eqbench_score | 0.697 | 0.000 |
| num_samples | 135.000 | 0.000 |

**Model:** qwen3-14b-nothink-arena
**Evaluation Time (hh:mm:ss):** N/A
**Temperature:** N/A
**Overlong samples:** 0.0% (0 / 135)

### gpqa_diamond

| Metric | Score | Std Error |
|--------|-------|----------|
| gpqa_pass@1:1_samples | 0.535 | 0.036 |
| gpqa_pass@1:4_samples | 0.537 | 0.028 |
| gpqa_pass@1:8_samples | 0.535 | 0.027 |

**Model:** qwen3-14b-reasoning
**Evaluation Time (hh:mm:ss):** 00:05:29
**Temperature:** 0.6
**Overlong samples:** 0.0% (0 / 1584)

### ifeval

| Metric | Score | Std Error |
|--------|-------|----------|
| prompt_level_strict_acc | 0.852 | 0.015 |
| inst_level_strict_acc | 0.900 | 0.000 |
| prompt_level_loose_acc | 0.880 | 0.014 |
| inst_level_loose_acc | 0.921 | 0.000 |

**Model:** qwen3-14b-reasoning
**Evaluation Time (hh:mm:ss):** 00:04:18
**Temperature:** 0.6
**Overlong samples:** 0.0% (0 / 541)

### lcb-v6-aug2024+

| Metric | Score | Std Error |
|--------|-------|----------|
| eval/pass_1 | 0.292 | 0.000 |
| eval/easy_pass_1 | 0.818 | 0.000 |
| eval/medium_pass_1 | 0.253 | 0.000 |
| eval/hard_pass_1 | 0.035 | 0.000 |
| eval/completion_length | 4999.486 | 0.000 |

**Model:** qwen-14b-nothink
**Evaluation Time (hh:mm:ss):** 01:39:33
**Temperature:** N/A
**Overlong samples:** 0.0% (0 / 7264)

### math_500

| Metric | Score | Std Error |
|--------|-------|----------|
| math_pass@1:1_samples | 0.900 | 0.013 |
| math_pass@1:4_samples | 0.885 | 0.012 |

**Model:** qwen3-14b-reasoning
**Evaluation Time (hh:mm:ss):** 00:03:27
**Temperature:** 0.6
**Overlong samples:** 0.0% (0 / 2000)

### mmlu_generative

| Metric | Score | Std Error |
|--------|-------|----------|
| extractive_match | 0.815 | 0.003 |

**Model:** qwen3-14b-reasoning
**Evaluation Time (hh:mm:ss):** 00:55:08
**Temperature:** 0.6
**Overlong samples:** 0.0% (0 / 14042)

### mmlu_pro

| Metric | Score | Std Error |
|--------|-------|----------|
| pass@1:1_samples | 0.701 | 0.004 |

**Model:** qwen3-14b-reasoning
**Evaluation Time (hh:mm:ss):** 00:49:51
**Temperature:** 0.6
**Overlong samples:** 0.0% (0 / 12032)

### musr_generative

| Metric | Score | Std Error |
|--------|-------|----------|
| extractive_match | 0.564 | 0.031 |

**Model:** qwen3-14b-reasoning
**Evaluation Time (hh:mm:ss):** 00:03:00
**Temperature:** 0.6
**Overlong samples:** 0.0% (0 / 756)

### obqa_generative

| Metric | Score | Std Error |
|--------|-------|----------|
| extractive_match | 0.940 | 0.011 |

**Model:** qwen3-14b-reasoning
**Evaluation Time (hh:mm:ss):** 00:01:59
**Temperature:** 0.6
**Overlong samples:** 0.0% (0 / 500)

### rewardbench

| Metric | Score | Std Error |
|--------|-------|----------|
| eval/percent_correct | 0.667 | 0.000 |
| eval/total_samples | 1865.000 | 0.000 |
| eval/correct_samples | 1244.000 | 0.000 |
| eval/format_compliance_rate | 0.999 | 0.000 |
| eval/avg_response_length | 1760.944 | 0.000 |
| eval/response_length_std | 1113.191 | 0.000 |
| eval/judgment_entropy | 1.337 | 0.000 |
| eval/most_common_judgment_freq | 0.393 | 0.000 |
| eval/format_error_rate | 0.001 | 0.000 |
| eval/avg_ties_rating | 4.939 | 0.000 |
| eval/ties_error_rate | 0.006 | 0.000 |
| eval/percent_correct_Factuality | 0.531 | 0.000 |
| eval/percent_correct_Precise IF | 0.344 | 0.000 |
| eval/percent_correct_Math | 0.601 | 0.000 |
| eval/percent_correct_Safety | 0.738 | 0.000 |
| eval/percent_correct_Focus | 0.814 | 0.000 |
| eval/percent_correct_Ties | 0.902 | 0.000 |
| eval/choice_samples | 1763.000 | 0.000 |
| eval/ties_samples | 102.000 | 0.000 |
| eval/choice_format_compliance_rate | 0.999 | 0.000 |
| eval/ties_format_compliance_rate | 1.000 | 0.000 |
| eval/wrong_answer_a_bias_rate | 0.552 | 0.000 |
| eval/wrong_answer_total_count | 611.000 | 0.000 |
| eval/wrong_answer_a_count | 337.000 | 0.000 |

**Model:** qwen3-14b-nothink-arena
**Evaluation Time (hh:mm:ss):** 00:09:42
**Temperature:** 0.6
**Overlong samples:** 0.0% (0 / 1865)

### simpleqa_nous

| Metric | Score | Std Error |
|--------|-------|----------|
| exact_match | 0.030 | 0.003 |
| fuzzy_match | 0.047 | 0.003 |

**Model:** qwen3-14b-reasoning
**Evaluation Time (hh:mm:ss):** 00:16:58
**Temperature:** 0.6
**Overlong samples:** 0.0% (0 / 4321)