Code Interpreter Benchmark
Qwen-14B 81.7% leads since September 2023 Models use a Python code interpreter for math, data visualization, and general tasks. Scoring covers result accuracy and the share of code that runs.
The visualization judge changed from Qwen-VL-Chat to GPT-4V in December 2023, so versions differ.
- Made by
- Qwen
- Released
- September 2023
- Kind
- Function calling
- Level
- School
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Strongest model tested
- Qwen-14B #213 on the capability index
- Last in a system card
- September 2023
- Last model added
- September 2023
Qwen-14B leads with 81.7% among models released by November 2023
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in November 2023, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
-
Gemini 4 Carbon - GPT-6 Astra
- Claude Opus 5.5
- and 16 more
Source: Labs’ model cards
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Labs’ model cards
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Labs’ model cards
Labs report it only in system cards
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.
3 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Sep 28, 2023 | Qwen-7B technical report | 70.2 | In-house Code Interpreter benchmark, executable code rate All (Math 82.4, Visualization 64.4, General 67.2) (Table 7). Final-response correctness: Math 41.9, Vis.-Hard 40.5, Vis.-Easy 54.4, Vis.-All 47.2 (Table 8) | Capabilities |
| Sep 28, 2023 | Qwen-14B technical report | 81.7 | In-house Code Interpreter benchmark, executable code rate All (Math 89.2, Visualization 84.1, General 65.5) (Table 7). Final-response correctness: Math 58.4, Vis.-Hard 53.6, Vis.-Easy 59.5, Vis.-All 56.4 (Table 8) | Capabilities |
| Sep 28, 2023 | Qwen-1_8B technical report | 26.8 | In-house Code Interpreter benchmark, executable code rate All (Math 33.8, Visualization 30.1, General 8.6) (Table 7). Final-response correctness: Math 14.7, Vis.-Hard 3.6, Vis.-Easy 20.3, Vis.-All 11.7 (Table 8) | Capabilities |
More in Tool use
- AutomationBench In use Agent completes end-to-end business workflows inside a simulated company exposing dozens of REST APIs. Graded on resulting state. Gemini 4 Carbon 53.9%
- MCP Atlas In use Multi-step workflows over real MCP servers. Scores tool-use competency on realistic tasks. Gemini 4 Argon 90.7%
- BFCL V4 In use Models call functions and tools, including multi-turn agentic tasks with web search and memory. Checked against expected calls and outcomes. Qwen3.7-Max 75%
- τ³-bench Banking In use Agents act as banking customer-service reps over many turns with a simulated user, following policy. Pass^1 on the final database state. Qwen 3.8 Max 55.1%
- Toolathlon-Verified In use 108 long-horizon tasks across 32 apps through about 600 MCP tools. Execution-based checkers inspect final environment state. GLM-5.3-Flash 78.4%
- DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%