SWE-bench Multilingual
SWE-bench Multilingual extends SWE-bench to multiple programming languages beyond Python.
Category
Agentic Coding
Max Score
100.0
Score Type
percent
Active
Yes
Model Scores
Scores for SWE-bench Multilingual
| Model | Score | Date | Verified |
|---|---|---|---|
| Qwen3.6-35B-A3B |
73.61%
|
16.04.2026 | Verified |
| Gemma4-31B-it |
55.27%
|
16.04.2026 | Unverified |
| Qwen3.5-35B-A3B |
65.44%
|
16.04.2026 | Unverified |
| Gemma4-26B-A4B |
14.56%
|
16.04.2026 | Unverified |
| Qwen3.6-27B |
78.46%
|
22.04.2026 | Verified |
| Qwen3.5-397B-A17B |
76.09%
|
22.04.2026 | Unverified |
| Claude 4.5 Opus |
85.80%
|
22.04.2026 | Unverified |
| Qwen3.5-27B |
76.09%
|
16.04.2026 | Unverified |
| Ornith-1.0-9B |
55.62%
|
25.06.2026 | Verified |
| Gemma4-12B |
32.54%
|
25.06.2026 | Unverified |
| Ornith-1.0-35B |
76.09%
|
25.06.2026 | Verified |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 |
74.20%
|
04.06.2026 | Verified |
| MiniMax-M2.7 |
79.05%
|
04.06.2026 | Unverified |
| GLM-5.1 |
82.60%
|
04.06.2026 | Unverified |
| Kimi K2.6 |
85.33%
|
04.06.2026 | Unverified |
| DeepSeek-V4-Pro |
84.62%
|
04.06.2026 | Unverified |
| DeepSeek-V4-Flash |
80.83%
|
26.06.2026 | Verified |
| DeepSeek-V3.2 |
67.81%
|
03.02.2026 | Verified |
| GLM-4.7 |
69.47%
|
03.02.2026 | Verified |
| MiniMax M2.1 |
72.43%
|
03.02.2026 | Verified |
| Ornith-1.5-35B-A3B |
78.58%
|
19.08.2026 | Verified |
| Ornith-1.0-35B-A3B |
76.09%
|
19.08.2026 | Unverified |
| Gemma-4-31B |
55.27%
|
19.08.2026 | Unverified |
| Claude Opus 4.6 |
86.15%
|
23.08.2026 | Verified |
| Gemini 3.1 Pro |
85.09%
|
23.08.2026 | Verified |
| Kimi K2.5 |
80.47%
|
23.08.2026 | Verified |
| Opus-4.6 |
85.80%
|
26.06.2026 | Verified |
| DeepSeek-V4-Pro |
84.26%
|
26.06.2026 | Verified |
| Qwen3.8-27B |
81.42%
|
26.08.2026 | Unverified |
| Qwen3.7-Plus |
83.79%
|
26.08.2026 | Unverified |
| Claude-Opus-4.6 (Max) |
85.80%
|
26.08.2026 | Unverified |
| Hy4 preview |
92.19%
|
28.08.2026 | Verified |
| DeepSeek V4 Pro |
85.56%
|
28.08.2026 | Verified |
| Qwen3.8-2.4T-A95B |
91.83%
|
28.08.2026 | Verified |
| GLM-5.3 |
90.30%
|
28.08.2026 | Verified |
| Kimi K3 |
89.70%
|
28.08.2026 | Verified |
| GPT-5.6 Sol |
81.78%
|
28.08.2026 | Verified |
| Spark-X2.5-4B |
57.16%
|
— | Verified |
| Spark-X2.5-1.7B |
21.66%
|
— | Verified |
| Qwen3.5-4B |
26.86%
|
— | Verified |
| Qwen3.5-2B |
5.00
|
— | Verified |
| Qwen3.5-9B |
45.33%
|
25.06.2026 | Verified |
| Qwen3-Coder-Next |
68.40%
|
03.02.2026 | Verified |
| Qwen3.8-Flash-Next |
89.94%
|
26.08.2026 | Verified |
| Hy3 |
83.79%
|
28.08.2026 | Verified |
| Claude Opus 5 |
100.00%
|
28.08.2026 | Verified |