SWE-1.6: benchmark scores, price and ranking

SWE-1.6 from Cognition ranks #543 of 743 LLMs on the LLMs Tiger aggregate benchmark score (46.0), based on 1 benchmark results captured up to 2026-10-13.

Organisation: Cognition
Type: Frontier model
Open weights: No
Released: 2026-04-07 (source: epoch)
Cheapest API price: $0.500 in / $2.50 out per million tokens (via cognition, observed 2026-10-13T21:47Z)
Aggregate rank: #543 of 743 (score 46.0)

Across the 1 benchmark where at least ten models are scored, SWE-1.6 is in the top 10% on 0 and in the top half on 0.

Its cheapest listed input price, $0.500 per million tokens, is lower than that of 48% of the 427 models with a listed price.

SWE-1.6 benchmark results

SWE-1.6 benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
FrontierCode	9.4%	#14 of 15	Epoch AI Benchmarking Hub	2026-10-13

About SWE-1.6

SWE-1.6 is a frontier model from Cognition. It was released on 2026-04-07, according to Epoch AI. The cheapest API listing we track charges $0.500 per million input tokens and $2.50 per million output tokens, through cognition. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.

Where SWE-1.6 stands

On our aggregate score, SWE-1.6 is #543 of 743 ranked models, in the lower half. Its score is 46.0; the scale is centred on 50, so it sits 4.0 points below the typical model. That beats 27% of the ranked field. Among the 3 ranked Cognition models it is #3. The next one up is SWE-1.7 at 50.8.

SWE-1.6, benchmark by benchmark

FrontierCode is a weak spot. SWE-1.6 scores 9.4%, #14 of 15, behind 87% of the models measured. The leader, Claude Opus 5 (max), reaches 53.4%. It covers hard programming tasks. The board median is 31.8%, so SWE-1.6 is 22.4 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so SWE-1.6 costs about the same as the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on Kimi K2 0905 (Novita) ($0.600) and nemotron-3-ultra ($0.600).

Release history

The next one was SWE-1.7 on 2026-07-08, at 50.8.

Reading these numbers

The 1 score on this page comes from 1 source: Epoch AI Benchmarking Hub (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 1 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#540 Mathstral-7B-v0.1 (46.1)
#541 MiMo-7B-Base (46.0)
#542 open-mixtral-8x22b (46.0)
#544 claude-opus-4-1-20250805_32K (46.0)
#545 Eurus-2-7B-PRIME (46.0)
#546 DeepSeek-Coder-V2-Lite-Instruct (46.0)