Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes
BenchLM

Scientific Code Benchmark (SciCode)

SciCode evaluates language models on generating code for realistic scientific research problems across 16 subfields of physics, math, chemistry, biology, and material science. Problems decompose into 338 subproblems requiring domain knowledge recall, scientific reasoning, and precise code synthesis. Based on real scripts from published research.

Data verified 33 confirmed releases in the last 30 daysSee provider release alerts

Top models on SciCode — September 15, 2026

As of September 15, 2026, Sakana Fugu leads the SciCode leaderboard with 60.1% , followed by Sakana Fugu-Ultra (58.7%) and Qwen3.7 Max (53.5%).

1Proprietary

Sakana Fugu

Sakana AI

60.1%
Context 1M
2Proprietary

Sakana Fugu-Ultra

Sakana AI

58.7%
Context 1M
3Proprietary

Qwen3.7 Max

Alibaba

53.5%
Overall 67.03Context 1M

27 modelsCoding10% of category scoreRefreshingUpdated September 15, 2026

Leaderboard (27 models)

Score
1
Sakana FuguSakana AI · Closed
60.1%
2
Sakana Fugu-UltraSakana AI · Closed
58.7%
3
Qwen3.7 MaxAlibaba · Closed
53.5%
4
Gemini 3.5 FlashGoogle · Closed
53.1%
5
Kimi K2.6Moonshot AI · Open weight
52.2%
6
Qwen3.7 PlusAlibaba · Closed
51.3%
7
Inkling-SmallThinking Machines Lab · Open weight
48.7%
8
Kimi K2.5Moonshot AI · Open weight
48.7%
9
Grok 4.3xAI · Closed
47.3%
10
Qwen 3.6 Max (preview)Alibaba · Closed
47%
11
Nemotron 3 UltraNVIDIA · Open weight
44.6%
12
Muse Glimmer 30BMeta · Open weight
43.6%
13
Ling 3.0 FlashInclusionAI · Open weight
41.2%
14
Hy3 PreviewTencent · Open weight
41.2%
15
A.X K2SK Telecom · Open weight
41%
16
Ling 3.0 Flash FP8InclusionAI · Open weight
40.4%
17
Granite 4.2 30BIBM · Open weight
38.8%
18
Mercury 2Inception · Closed
38.4%
19
Mercury 2.5Inception · Closed
38%
20
K-EXAONE 2.0LG AI Research · Open weight
37.4%
21
Granite 4.2 8BIBM · Open weight
36.1%
22
Nemotron 3 Nano Omni 30B A3BNVIDIA · Open weight
32%
23
Nemotron 3.5 Lightning 30B A3B NVFP4NVIDIA · Open weight
31.4%
24
Agents-A1-4BInternScience · Open weight
29.6%
25
Ling 2.6 FlashInclusionAI · Open weight
27%
26
MiniCPM5-2BOpenBMB · Open weight
26.3%
27
Granite 4.2 3BIBM · Open weight
24.1%

According to BenchLM.ai, Sakana Fugu leads the SciCode benchmark with a score of 60.1%, followed by Sakana Fugu-Ultra (58.7%) and Qwen3.7 Max (53.5%). The scores show moderate spread, with meaningful differences between the top tier and mid-tier models.

27 models have been evaluated on SciCode. The benchmark falls in the Coding category. This category carries a 20% weight in BenchLM.ai's overall scoring system. Within that category, SciCode contributes 10% of the category score, so strong performance here directly affects a model's overall ranking.

About SciCode

Year

2024

Tasks

80

BenchLM freshness & provenance

Version

SciCode 2024

Refresh cadence

Annual

Staleness state

Refreshing

Question availability

Public benchmark set

Refreshing

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does SciCode measure?

SciCode evaluates language models on generating code for realistic scientific research problems across 16 subfields of physics, math, chemistry, biology, and material science. Problems decompose into 338 subproblems requiring domain knowledge recall, scientific reasoning, and precise code synthesis. Based on real scripts from published research.

Which model scores highest on SciCode?

Sakana Fugu by Sakana AI currently leads with a score of 60.1% on SciCode.

How many models are evaluated on SciCode?

27 AI models have been evaluated on SciCode on BenchLM.

Compare Top Models on SciCode

Sakana Fugu vs Sakana Fugu-UltraSakana Fugu-Ultra vs Qwen3.7 MaxQwen3.7 Max vs Gemini 3.5 FlashGemini 3.5 Flash vs Kimi K2.6
Last updated: September 15, 2026 · BenchLM version SciCode 2024

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.