SWE-bench Pro Results Across LLMs

89.9% · raw 89.9 %

Headline · unknown effort · Peer vendor

Source/record date: 2026-09-27

As reported by NaiveAI; card cites the Opus 5.5 system card.

81.3% · raw 81.3 %

Headline · max effort · Own vendor

Source/record date: 2026-09-28

SWE-bench Pro avg over 5 trials; standard config (adaptive thinking max)

73.6% · raw 73.6 %

Headline · unknown effort · Own vendor

Source/record date: 2026-09-27

PDF chart text and figure pixels read 73.6; the release page alt text says 68.8 and looks stale. Chart value used; harness Claude Code 2.1.207.

67.7% · raw 67.7 %

Headline · unknown effort · Third-party

Source/record date: 2026-09-02

SWE-Pro / SWE-bench Pro

67.7% · raw 67.7 %

Alternative · unknown effort · Peer vendor

Source/record date: 2026-09-08

As reported in Nex-N2.5-Pro model card comparison table | Demoted 2026-09-25: duplicate of headline from Alibaba Qwen3.8-Max-0902 comparison table via DataCamp; vendor official preferred over Nex-N2.5-Pro peer comparison table (rule a); same value.

67.7% · raw 67.7 %

Alternative · unknown effort · Peer vendor

Source/record date: 2026-09-27

As reported by NaiveAI. Chart labels Qwen-3.8-Max; attached to the 0902 snapshot with version ambiguity noted.

65.7% · raw 65.7 %

Headline · unknown effort · Own vendor

Source/record date: 2026-08-28

Vendor chart transcription

65.7% · raw 65.7 %

Alternative · unknown effort · Peer vendor

Source/record date: 2026-09-27

As reported by NaiveAI.

64.6% · raw 64.6 %

Headline · unknown effort · Peer vendor

Source/record date: 2026-09-08

As reported in Nex-N2.5-Pro model card comparison table

63.4% · raw 63.4 %

Headline · unknown effort · Own vendor

Source/record date: 2026-07-09

63.3% · raw 63.3 %

Headline · xhigh effort · Third-party

Source/record date: 2026-09-18

SWE-bench Pro — launch secondary transcription

62.5% · raw 62.5 %

Headline · xhigh effort · Own vendor

Source/record date: 2026-08-26

SWE-bench Pro — QwenCloud latest-model page

61.7% · raw 61.7 %

Headline · unknown effort · Own vendor

Source/record date: 2026-08-14

SWE-bench Pro; Claude Code harness (temp=1.0, top_p=0.95, 256K) except Opus uses official

61.2% · raw 61.2 %

Headline · unknown effort · Own vendor

Source/record date: 2026-09-08

NexAU harness

44.6% · raw 44.6 %

Headline · unknown effort · Own vendor

Source/record date: 2026-09-21

Released SFT checkpoint, avg@3; MiMo-V2.6 tech report Table 6 (https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL/blob/main/MiMo_V2_6_technical_report.pdf) and HF card Evaluation table. Also plotted (SFT line) in radar figure on https://mimo.mi.com/docs/en-US/news/latest/v2-6. Eval effort not specified (thinking model). HF card label 'SWE Pro'.

45.2% · raw 45.2 %

Alternative · unknown effort · Own vendor

Source/record date: 2026-09-21

Harness: mini-harness1 (training harness). SFT checkpoint, tech report Table 7 (coding performance across agent harnesses; PDF p.36). Not the headline (headline = Table 6 / HF card).

46.6% · raw 46.6 %

Alternative · unknown effort · Own vendor

Source/record date: 2026-09-21

Harness: mini-harness2 (training harness). SFT checkpoint, tech report Table 7 (coding performance across agent harnesses; PDF p.36). Not the headline (headline = Table 6 / HF card).

45.1% · raw 45.1 %

Alternative · unknown effort · Own vendor

Source/record date: 2026-09-21

Harness: mini-harness3 (training harness). SFT checkpoint, tech report Table 7 (coding performance across agent harnesses; PDF p.36). Not the headline (headline = Table 6 / HF card).

45.5% · raw 45.5 %

Alternative · unknown effort · Own vendor

Source/record date: 2026-09-21

Harness: mini-harness4 (training harness). SFT checkpoint, tech report Table 7 (coding performance across agent harnesses; PDF p.36). Not the headline (headline = Table 6 / HF card).

40.3% · raw 40.3 %

Alternative · unknown effort · Own vendor

Source/record date: 2026-09-21

Harness: codex (held-out harness). SFT checkpoint, tech report Table 7 (coding performance across agent harnesses; PDF p.36). Not the headline (headline = Table 6 / HF card).

42.2% · raw 42.2 %

Alternative · unknown effort · Own vendor

Source/record date: 2026-09-21

Harness: claude code (held-out harness). SFT checkpoint, tech report Table 7 (coding performance across agent harnesses; PDF p.36). Not the headline (headline = Table 6 / HF card).

45.6% · raw 45.6 %

Alternative · unknown effort · Own vendor

Source/record date: 2026-09-21

Harness: mini-swe-agent (held-out harness). SFT checkpoint, tech report Table 7 (coding performance across agent harnesses; PDF p.36). Not the headline (headline = Table 6 / HF card).

44.4% · raw 44.4 %

Alternative · unknown effort · Own vendor

Source/record date: 2026-09-21

Harness: Mean (7 harnesses) (unweighted mean). SFT checkpoint, tech report Table 7 (coding performance across agent harnesses; PDF p.36). Not the headline (headline = Table 6 / HF card).