SWE-1.7: benchmark scores, price and ranking

SWE-1.7 from Cognition ranks #167 of 743 LLMs on the LLMs Tiger aggregate benchmark score (50.8), based on 1 benchmark results captured up to 2026-10-13.

Organisation: Cognition
Type: Frontier model
Open weights: No
Released: 2026-07-08 (source: epoch)
Cheapest API price: $0.500 in / $2.50 out per million tokens (via cognition, observed 2026-10-13T20:47Z)
Aggregate rank: #167 of 743 (score 50.8)

Across the 1 benchmark where at least ten models are scored, SWE-1.7 is in the top 10% on 0 and in the top half on 1.

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-1.7 benchmark results

SWE-1.7 benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
FrontierCode	42.0%	#6 of 15	Epoch AI Benchmarking Hub	2026-10-13

About SWE-1.7

SWE-1.7 is a frontier model from Cognition. It was released on 2026-07-08, 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-1.7 stands

On our aggregate score, SWE-1.7 is #167 of 743 ranked models, in the top quarter. Its score is 50.8; the scale is centred on 50, so it sits 0.8 points above the typical model. That beats 78% of the ranked field. Among the 3 ranked Cognition models it is #2. The next one up is SWE-2 (max) at 51.9. The next one down is SWE-1.6 at 46.0.

SWE-1.7, benchmark by benchmark

FrontierCode puts SWE-1.7 at 42.0%, #6 of 15. That beats 60% of the models tested, but 11.4 points short of Claude Opus 5 (max) (53.4%). The results either side are GPT-6 Luna (max) (42.4%) and GLM-5.3 (max) (40.1%). It covers hard programming tasks. The board median is 31.8%, so SWE-1.7 is 10.2 points above 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-1.7 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 Flash 0731 (max) ($0.016, 53.1), GLM-5.3-Flash (max) ($0.026, 49.6). Similar scores cost more on Kimi K2 ($0.550) and MiniMax-M1-80k ($0.550).

Release history

The Cognition model released before it was SWE-1.6 on 2026-04-07, which scores 46.0. The next one was SWE-2 (max) on 2026-09-10, at 51.9.

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

#164 GPT-4 (0613) (50.8)
#165 Claude Code + GLM-5.3 (50.8)
#166 gpt-4-0314 (50.8)
#168 claude-3-5-haiku-20241022 (50.8)
#169 DeepSeek V3 0324 (50.8)
#170 o3-mini_1.0 (50.7)