Noometry

Model comparison

GPT-3.5-turbo vs Mercury 2

Mercury 2 is the stronger model overall, scoring 39.1 to 23.2 on the Noometry Index.

Last verified . 12 shared benchmarks.

GPT-3.5-turbo OpenAI

23.2

Rank #350 Confirmed

Mercury 2 Inception

39.1

Rank #175 Confirmed

Summary

  • They share 12 benchmarks with published results for both. GPT-3.5-turbo scores higher in 0 categories and Mercury 2 in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Mercury 2 leads 53.8 to 25.3.
  • The biggest single-benchmark swing is WeirdML: 3.5% for GPT-3.5-turbo and 43.2% for Mercury 2.
  • Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.50 / $1.50 for GPT-3.5-turbo.
  • Mercury 2 accepts more context: 128K tokens versus 16K.

Side by side

GPT-3.5-turboMercury 2
ProviderOpenAIInception
Noometry Index23.239.1
Released2023-03-012026-02-20
WeightsProprietaryProprietary
Context window16K128K
Max output4K50K
Input $ / M tokens$0.50$0.25
Output $ / M tokens$1.50$0.75
Results tracked4417

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Mercury 2 leads

GPT-3.5-turbo: 23.9 (#331), Mercury 2: 33.5 (#255)

BenchmarkGPT-3.5-turboMercury 2
WeirdML3.5%43.2%
LMArena Coding11361391
LMArena WebDev—1171
SciCode—38.7%
BigCodeBench Instruct39.1%—
BigCodeBench Complete50.6%—
ALE-Bench—785.58
HumanEval+70.7%—
MBPP+69.7%—

Agentic & Tool Use Not comparable

GPT-3.5-turbo: —, Mercury 2: —

BenchmarkGPT-3.5-turboMercury 2
METR Time Horizons21.5%—

Reasoning Mercury 2 leads

GPT-3.5-turbo: 13.8 (#332), Mercury 2: 23.8 (#170)

BenchmarkGPT-3.5-turboMercury 2
LMArena Hard Prompts11081362
CritPt—0.8%
Chess Puzzles0%—
Mystery Game Puzzles3%—
DTBench48.5%—
LMCA9.7%—
Adversarial NLI58.1%—
BIG-Bench Hard61.6%—
CommonsenseQA 2.057%—
Epoch Capabilities Index118.55—
ForecastBench50.4—
WinoGrande81.6%—

Math Not comparable

GPT-3.5-turbo: 6.3 (#327), Mercury 2: —

BenchmarkGPT-3.5-turboMercury 2
FrontierMath (Tiers 1-3)0%—
OTIS Mock AIME 2024-20252.2%—
LMArena Math1142—
MATH Level 515.9%—
GSM8K57.8%—

Knowledge Mercury 2 leads

GPT-3.5-turbo: 10.0 (#303), Mercury 2: 36.2 (#172)

BenchmarkGPT-3.5-turboMercury 2
LMArena Expert10701358
GPQA Diamond28%—
Vectara Hallucination Rate—12.3%
ARC (AI2) Challenge87.4%—
BoolQ87%—
MMLU71.4%—
OpenBookQA86%—
TriviaQA85.8%—

Multilingual Mercury 2 leads

GPT-3.5-turbo: 31.5 (#258), Mercury 2: 46.6 (#157)

BenchmarkGPT-3.5-turboMercury 2
LMArena Non-English11081331
LMArena Chinese10751417
LMArena Russian11231304
LMArena French1118—
LMArena German1090—
LMArena Japanese1043—
LMArena Korean1019—
LMArena Spanish1121—

Instruction Following Mercury 2 leads

GPT-3.5-turbo: 57.9 (#262), Mercury 2: 70.2 (#165)

BenchmarkGPT-3.5-turboMercury 2
LMArena Instruction Following11191329

Long Context Mercury 2 leads

GPT-3.5-turbo: 34.0 (#254), Mercury 2: 40.5 (#154)

BenchmarkGPT-3.5-turboMercury 2
LMArena Longer Query11211330

Writing & Preference Mercury 2 leads

GPT-3.5-turbo: 25.3 (#305), Mercury 2: 53.8 (#155)

BenchmarkGPT-3.5-turboMercury 2
LMArena Text11251355
LMArena Creative Writing10921289
LMArena Multi-Turn11171358
EQ-Bench Creative Writing451—

Frequently asked questions

Is GPT-3.5-turbo better than Mercury 2?

Mercury 2 is the stronger model overall, scoring 39.1 to 23.2 on the Noometry Index.

Which is cheaper, GPT-3.5-turbo or Mercury 2?

Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GPT-3.5-turbo lists at $0.50 and $1.50.

Is GPT-3.5-turbo or Mercury 2 better for coding?

Mercury 2 scores higher on coding benchmarks: 33.5 versus 23.9 in the Noometry coding category.

Which has the bigger context window?

Mercury 2 does, with 128K tokens against 16K.

How many benchmarks do GPT-3.5-turbo and Mercury 2 share?

12 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and Mercury 2 has 17.

Related comparisons

Go deeper