Math Reasoning on MathBench EN
50.6ScoreInternLM2-Chat-20B-SFT
Evaluation results
| Method | Links | |
|---|---|---|
| InternLM2-Chat-20B-SFTModel Category=~20B Models, Shot Count=0-shot&8-shot2024.03 | 50.6 | |
| GLM4.5-V-106B-A12B + GeoTikzBridge-BaseTikz-supplementation=true2026.03 | 49.8 | |
| InternLM2-Chat-20BModel Category=~20B Models, Shot Count=0-shot&8-shot2024.03 | 48.5 | |
| Mixtral-8x7B-Instruct-v0.1Model Category=~20B Models, Shot Count=0-shot&8-shot2024.03 | 44.3 | |
| Skywork-OR1-32B + GeoTikzBridge-BaseTikz-supplementation=true2026.03 | 43.6 | |
| GLM4.5-V-106B-A12BTikz-supplementation=false2026.03 | 43.4 | |
| GPT-OSS-120B + GeoTikzBridge-BaseTikz-supplementation=true2026.03 | 43 | |
| GPT-3.5Model Category=API Models, Shot Count=0-shot&8-shot2024.03 | 42.5 | |
| InternLM2-Chat-7BModel Category=~7BModels, Shot Count=0-shot&8-shot2024.03 | 42.3 | |
| Qwen-14B-ChatModel Category=~20B Models, Shot Count=0-shot&8-shot2024.03 | 40.6 | |
| InternLM2-Chat-7B-SFTModel Category=~7BModels, Shot Count=0-shot&8-shot2024.03 | 40.1 | |
| Claude3.5-SonnetTikz-supplementation=false2026.03 | 39.7 | |
| InternVL3-78BTikz-supplementation=false2026.03 | 39.7 | |
| Qwen3-30B-A3B + GeoTikzBridge-BaseTikz-supplementation=true2026.03 | 39.7 | |
| InternVL3.5-38B + GeoTikzBridge-BaseTikz-supplementation=true2026.03 | 36.9 | |
| DS-R1-Distill-Qwen-32B + GeoTikzBridge-BaseTikz-supplementation=true2026.03 | 36.4 | |
| Qwen2.5-VL-32BTikz-supplementation=false2026.03 | 35.9 | |
| GLM-4.5-Air-106B-A12B + GeoTikzBridge-BaseTikz-supplementation=true2026.03 | 35.9 | |
| Gemini-1.5-ProTikz-supplementation=false2026.03 | 35.5 | |
| InternVL3.5-38BTikz-supplementation=false2026.03 | 35.3 | |
| GPT-4oTikz-supplementation=false2026.03 | 33.4 | |
| Qwen3-VL-30B-A3B + GeoTikzBridge-BaseTikz-supplementation=true2026.03 | 32 | |
| Qwen3-VL-30B-A3BTikz-supplementation=false2026.03 | 31.4 | |
| GLM-Z1-32B + GeoTikzBridge-BaseTikz-supplementation=true2026.03 | 30.5 | |
| Qwen2.5-VL-72BTikz-supplementation=false2026.03 | 30.4 | |
| Baichuan2-13B-ChatModel Category=~20B Models, Shot Count=0-shot&8-shot2024.03 | 29.1 | |
| Qwen-7B-ChatModel Category=~7BModels, Shot Count=0-shot&8-shot2024.03 | 29 | |
| Mistral-7B-Instruct-v0.2Model Category=~7BModels, Shot Count=0-shot&8-shot2024.03 | 28.3 | |
| ChatGLM3-6BModel Category=~7BModels, Shot Count=0-shot&8-shot2024.03 | 21.7 | |
| Baichuan2-7B-ChatModel Category=~7BModels, Shot Count=0-shot&8-shot2024.03 | 17.8 | |
| Llama2-13B-ChatModel Category=~20B Models, Shot Count=0-shot&8-shot2024.03 | 15.7 | |
| Llama2-7B-ChatModel Category=~7BModels, Shot Count=0-shot&8-shot2024.03 | 7.7 |