Coding · Benchmark profile

Scientific Code Benchmark

Reference2024Active13 models

Data verified 21 Jul 2026 · Methodology 1.6.0

Benchmark score on Scientific Code Benchmark

Leaderboard · 13 models

Sakana Fugu leads at 60.1%, followed by Sakana Fugu-Ultra (58.7%) and Qwen3.7-Max (53.5%).

Display onlyCoding2024

#1Closed

Sakana Fugu

Sakana AI

sakana-fugu

60.1%

Overall — · Context 1M tokens

#2Closed

Sakana Fugu-Ultra

Sakana AI

sakana-fugu-ultra

58.7%

Overall — · Context 1M tokens

#3Closed

Qwen3.7-Max

Alibaba Cloud

qwen3.7-max

53.5%

Overall #37 · Context 1M tokens

Visual analysis

See the field.

Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.

ViewModelsColours

Sakana AIAlibaba CloudGoogleMoonshot AIxAINVIDIATencentInclusionAI

Scientific Code Benchmark leaderboard

13 ranked models · higher is better

View accessible chart data

Accessible data for Scientific Code Benchmark leaderboard
Model	Rank	Provider	Score
Sakana Fugu	#1	Sakana AI	60.1%
Sakana Fugu-Ultra	#2	Sakana AI	58.7%
Qwen3.7-Max	#3	Alibaba Cloud	53.5%
Gemini 3.5 Flash	#4	Google	53.1%
Kimi K2.6	#5	Moonshot AI	52.2%
Qwen3.7-Plus	#6	Alibaba Cloud	51.3%
Kimi K2.5	#7	Moonshot AI	48.7%
Grok 4.3	#8	xAI	47.3%
Qwen 3.6 Max (preview)	#9	Alibaba Cloud	47%
Nemotron 3 Ultra	#10	NVIDIA	44.6%
Hy3 Preview	#11	Tencent	41.2%
Nemotron 3 Nano Omni 30B A3B	#12	NVIDIA	32%
Ling 2.6 Flash	#13	InclusionAI	27%

Benchmark score table (13 models)

One best score per model · higher is better

Scientific Code Benchmark leaderboard ranked by score
Rank	Model	Provider	License	Evidence use	Score
#1	Sakana Fugu sakana-fugu	Sakana AI	closed	Estimated reference	60.1%
#2	Sakana Fugu-Ultra sakana-fugu-ultra	Sakana AI	closed	Estimated reference	58.7%
#3	Qwen3.7-Max qwen3.7-max	Alibaba Cloud	—	Reference only	53.5%
#4	Gemini 3.5 Flash gemini-3.5-flash	Google	closed	Estimated reference	53.1%
#5	Kimi K2.6 kimi-k2.6	Moonshot AI	open	Estimated reference	52.2%
#6	Qwen3.7-Plus qwen3.7-plus	Alibaba Cloud	—	Reference only	51.3%
#7	Kimi K2.5 kimi-k2.5	Moonshot AI	—	Reference only	48.7%
#8	Grok 4.3 grok-4.3	xAI	closed	Reference only	47.3%
#9	Qwen 3.6 Max (preview) qwen3-6-max-preview	Alibaba Cloud	closed	Reference only	47%
#10	Nemotron 3 Ultra nemotron-3-ultra-550b	NVIDIA	open	Estimated reference	44.6%
#11	Hy3 Preview hy3-preview	Tencent	open	Estimated reference	41.2%
#12	Nemotron 3 Nano Omni 30B A3B nemotron-3-nano-omni-30b-a3b	NVIDIA	open	Estimated reference	32%
#13	Ling 2.6 Flash ling-2-6-flash	InclusionAI	open	Estimated reference	27%

The top of this snapshot is led by Sakana Fugu at 60.1%; third place is 6.6 points behind. The top-10 spread is 15.5 points.

Compare top models

Sakana Fugu vs Sakana Fugu-Ultra Sakana Fugu-Ultra vs Qwen3.7-Max Qwen3.7-Max vs Gemini 3.5 Flash Gemini 3.5 Flash vs Kimi K2.6

About Scientific Code Benchmark

Definition and scoring

Organisation: BenchLM registry
Category: Coding
Version: 2024
Direction: higher is better
Ranking use: Reference
Contamination risk: Unknown

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. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.

Open benchmark source ↗

FAQ

Quick answers

What does Scientific Code Benchmark measure?

Which model scores highest on Scientific Code Benchmark?

Sakana Fugu by Sakana AI currently leads with 60.1%.

How many models are evaluated on Scientific Code Benchmark?

13 models in the LuminaBench cohort have a qualifying score on this benchmark.

LiveCodeBench

Rolling · 44 results · Weighted 3.2%

SWE-bench Verified

Verified · 79 results · Weighted 3.2%

CRUXEval

Rolling · Not evaluated · Not Weighted

SciCode

Rolling · 238 results · Weighted 3.2%

BigCodeBench

Rolling · 2 results · Not Weighted

SWE-Bench Pro

v1 · 92 results · Weighted 3.2%

Coding · Benchmark profile

Scientific Code Benchmark

Reference2024Active13 models

Data verified 21 Jul 2026 · Methodology 1.6.0

Benchmark score on Scientific Code Benchmark

Leaderboard · 13 models

Sakana Fugu leads at 60.1%, followed by Sakana Fugu-Ultra (58.7%) and Qwen3.7-Max (53.5%).

Display onlyCoding2024

#1Closed

Sakana Fugu

Sakana AI

sakana-fugu

60.1%

Overall — · Context 1M tokens

#2Closed

Sakana Fugu-Ultra

Sakana AI

sakana-fugu-ultra

58.7%

Overall — · Context 1M tokens

#3Closed

Qwen3.7-Max

Alibaba Cloud

qwen3.7-max

53.5%

Overall #37 · Context 1M tokens

Visual analysis

See the field.

Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.

ViewModelsColours

Sakana AIAlibaba CloudGoogleMoonshot AIxAINVIDIATencentInclusionAI

Scientific Code Benchmark leaderboard

13 ranked models · higher is better

View accessible chart data

Accessible data for Scientific Code Benchmark leaderboard
Model	Rank	Provider	Score
Sakana Fugu	#1	Sakana AI	60.1%
Sakana Fugu-Ultra	#2	Sakana AI	58.7%
Qwen3.7-Max	#3	Alibaba Cloud	53.5%
Gemini 3.5 Flash	#4	Google	53.1%
Kimi K2.6	#5	Moonshot AI	52.2%
Qwen3.7-Plus	#6	Alibaba Cloud	51.3%
Kimi K2.5	#7	Moonshot AI	48.7%
Grok 4.3	#8	xAI	47.3%
Qwen 3.6 Max (preview)	#9	Alibaba Cloud	47%
Nemotron 3 Ultra	#10	NVIDIA	44.6%
Hy3 Preview	#11	Tencent	41.2%
Nemotron 3 Nano Omni 30B A3B	#12	NVIDIA	32%
Ling 2.6 Flash	#13	InclusionAI	27%

Benchmark score table (13 models)

One best score per model · higher is better

Scientific Code Benchmark leaderboard ranked by score
Rank	Model	Provider	License	Evidence use	Score
#1	Sakana Fugu sakana-fugu	Sakana AI	closed	Estimated reference	60.1%
#2	Sakana Fugu-Ultra sakana-fugu-ultra	Sakana AI	closed	Estimated reference	58.7%
#3	Qwen3.7-Max qwen3.7-max	Alibaba Cloud	—	Reference only	53.5%
#4	Gemini 3.5 Flash gemini-3.5-flash	Google	closed	Estimated reference	53.1%
#5	Kimi K2.6 kimi-k2.6	Moonshot AI	open	Estimated reference	52.2%
#6	Qwen3.7-Plus qwen3.7-plus	Alibaba Cloud	—	Reference only	51.3%
#7	Kimi K2.5 kimi-k2.5	Moonshot AI	—	Reference only	48.7%
#8	Grok 4.3 grok-4.3	xAI	closed	Reference only	47.3%
#9	Qwen 3.6 Max (preview) qwen3-6-max-preview	Alibaba Cloud	closed	Reference only	47%
#10	Nemotron 3 Ultra nemotron-3-ultra-550b	NVIDIA	open	Estimated reference	44.6%
#11	Hy3 Preview hy3-preview	Tencent	open	Estimated reference	41.2%
#12	Nemotron 3 Nano Omni 30B A3B nemotron-3-nano-omni-30b-a3b	NVIDIA	open	Estimated reference	32%
#13	Ling 2.6 Flash ling-2-6-flash	InclusionAI	open	Estimated reference	27%

The top of this snapshot is led by Sakana Fugu at 60.1%; third place is 6.6 points behind. The top-10 spread is 15.5 points.

Compare top models

Sakana Fugu vs Sakana Fugu-Ultra Sakana Fugu-Ultra vs Qwen3.7-Max Qwen3.7-Max vs Gemini 3.5 Flash Gemini 3.5 Flash vs Kimi K2.6

About Scientific Code Benchmark

Definition and scoring

Organisation: BenchLM registry
Category: Coding
Version: 2024
Direction: higher is better
Ranking use: Reference
Contamination risk: Unknown

Open benchmark source ↗

FAQ

Quick answers

What does Scientific Code Benchmark measure?

Which model scores highest on Scientific Code Benchmark?

Sakana Fugu by Sakana AI currently leads with 60.1%.

How many models are evaluated on Scientific Code Benchmark?

13 models in the LuminaBench cohort have a qualifying score on this benchmark.

LiveCodeBench

Rolling · 44 results · Weighted 3.2%

SWE-bench Verified

Verified · 79 results · Weighted 3.2%

CRUXEval

Rolling · Not evaluated · Not Weighted

SciCode

Rolling · 238 results · Weighted 3.2%

BigCodeBench

Rolling · 2 results · Not Weighted

SWE-Bench Pro

v1 · 92 results · Weighted 3.2%

Search LUMINA BENCH

Navigation

Scientific Code Benchmark

Leaderboard · 13 models

Sakana Fugu

Sakana Fugu-Ultra

Qwen3.7-Max

See the field.

Scientific Code Benchmark leaderboard

Crop Scientific Code Benchmark leaderboard

Benchmark score table (13 models)

Crop Scientific Code Benchmark benchmark table

Compare top models

Definition and scoring

Quick answers

What does Scientific Code Benchmark measure?

Which model scores highest on Scientific Code Benchmark?

How many models are evaluated on Scientific Code Benchmark?

Scientific Code Benchmark

Leaderboard · 13 models

Sakana Fugu

Sakana Fugu-Ultra

Qwen3.7-Max

See the field.

Scientific Code Benchmark leaderboard

Crop Scientific Code Benchmark leaderboard

Benchmark score table (13 models)

Crop Scientific Code Benchmark benchmark table

Compare top models

Definition and scoring

Quick answers

What does Scientific Code Benchmark measure?

Which model scores highest on Scientific Code Benchmark?

How many models are evaluated on Scientific Code Benchmark?

Leaderboard · 13 models

Sakana Fugu

Sakana Fugu-Ultra

Qwen3.7-Max

See the field.

Benchmark score table (13 models)

Compare top models

Definition and scoring

Quick answers

What does Scientific Code Benchmark measure?

Which model scores highest on Scientific Code Benchmark?

How many models are evaluated on Scientific Code Benchmark?

More Coding benchmarks

Leaderboard · 13 models

Sakana Fugu

Sakana Fugu-Ultra

Qwen3.7-Max

See the field.

Benchmark score table (13 models)

Compare top models

Definition and scoring

Quick answers

What does Scientific Code Benchmark measure?

Which model scores highest on Scientific Code Benchmark?

How many models are evaluated on Scientific Code Benchmark?

More Coding benchmarks